{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/fine-grained-image-classification","name":"Fine-Grained Image Classification","slug":"fine-grained-image-classification","description_markdown":"**Fine-Grained Image Classification** is a task in computer vision where the goal is to classify images into subcategories within a larger category. For example, classifying different species of birds or different types of flowers. This task is considered to be fine-grained because it requires the model to distinguish between subtle differences in visual appearance and patterns, making it more challenging than regular image classification tasks.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Looking for the Devil in the Details](https://arxiv.org/pdf/1903.06150v2.pdf) )</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":353,"papers_with_code":200,"benchmarks":36,"benchmark_tables_in_archive":36,"benchmark_tables_shown":36,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":41,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/fine-grained-image-classification-on-stanford","slug":"fine-grained-image-classification-on-stanford","dataset":"Stanford Cars","dataset_url":"/dataset/stanford-cars","rows_in_archive":83,"metrics":["Accuracy","FLOPS","PARAMS"],"first_row_in_archive_order":{"model":"TResnet-L + PMD","paper_title":"Progressive Multi-task Anti-Noise Learning and Distilling Frameworks for Fine-grained Vehicle Recognition","paper_url":"/paper/progressive-multi-task-anti-noise-learning","paper_date":"2024-01-25","arxiv_id":"2401.14336","code_links":[{"title":"dichao-liu/anti-noise_fgvr","url":"https://github.com/dichao-liu/anti-noise_fgvr"}],"syntology":null}},{"leaderboard":"/sota/fine-grained-image-classification-on-fgvc","slug":"fine-grained-image-classification-on-fgvc","dataset":"FGVC Aircraft","dataset_url":"/dataset/fgvc-aircraft-1","rows_in_archive":57,"metrics":["Accuracy","Top-1 Error Rate","FLOPS","PARAMS","Top-1"],"first_row_in_archive_order":{"model":"I2-HOFI","paper_title":"Interweaving Insights: High-Order Feature Interaction for Fine-Grained Visual Recognition","paper_url":"/paper/interweaving-insights-high-order-feature","paper_date":"2024-10-20","arxiv_id":null,"code_links":[{"title":"arindam-1991/i2-hofi","url":"https://github.com/arindam-1991/i2-hofi"}],"syntology":null}},{"leaderboard":"/sota/fine-grained-image-classification-on-cub-200-1","slug":"fine-grained-image-classification-on-cub-200-1","dataset":"CUB-200-2011","dataset_url":"/dataset/cub-200-2011","rows_in_archive":30,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"HERBS","paper_title":"Fine-grained Visual Classification with High-temperature Refinement and Background Suppression","paper_url":"/paper/fine-grained-visual-classification-with-high-1","paper_date":"2023-03-11","arxiv_id":"2303.06442","code_links":[{"title":"chou141253/FGVC-HERBS","url":"https://github.com/chou141253/FGVC-HERBS"}],"syntology":null}},{"leaderboard":"/sota/fine-grained-image-classification-on-nabirds","slug":"fine-grained-image-classification-on-nabirds","dataset":"NABirds","dataset_url":"/dataset/nabirds","rows_in_archive":30,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"MetaFormer\n(MetaFormer-2,384)","paper_title":"MetaFormer: A Unified Meta Framework for Fine-Grained Recognition","paper_url":"/paper/metaformer-a-unified-meta-framework-for-fine","paper_date":"2022-03-05","arxiv_id":"2203.02751","code_links":[{"title":"dqshuai/metaformer","url":"https://github.com/dqshuai/metaformer"},{"title":"salluru007/papers","url":"https://github.com/salluru007/papers"}],"syntology":{"n":14,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/metaformer-a-unified-meta-framework-for-fine#ran","syntology_url":"https://syntology.ai/paper/2203.02751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.02751"}},"official":{"repos":["dqshuai/metaformer"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/fine-grained-image-classification-on-oxford","slug":"fine-grained-image-classification-on-oxford","dataset":"Oxford 102 Flowers","dataset_url":"/dataset/oxford-102-flower","rows_in_archive":25,"metrics":["Accuracy","Top-1 Error Rate","FLOPS","PARAMS","Top 1 Accuracy"],"first_row_in_archive_order":{"model":"IELT","paper_title":"Fine-Grained Visual Classification via Internal Ensemble Learning Transformer","paper_url":"/paper/fine-grained-visual-classification-via-2","paper_date":"2023-02-13","arxiv_id":null,"code_links":[{"title":"mobulan/ielt","url":"https://github.com/mobulan/ielt"}],"syntology":null}},{"leaderboard":"/sota/fine-grained-image-classification-on-stanford-1","slug":"fine-grained-image-classification-on-stanford-1","dataset":"Stanford Dogs","dataset_url":"/dataset/stanford-dogs","rows_in_archive":24,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"MP","paper_title":"SR-GNN: Spatial Relation-aware Graph Neural Network for Fine-Grained Image Categorization","paper_url":"/paper/sr-gnn-spatial-relation-aware-graph-neural","paper_date":"2022-09-05","arxiv_id":"2209.02109","code_links":[{"title":"ardhendubehera/sr-gnn","url":"https://github.com/ardhendubehera/sr-gnn"}],"syntology":null}},{"leaderboard":"/sota/fine-grained-image-classification-on-oxford-2","slug":"fine-grained-image-classification-on-oxford-2","dataset":"Oxford-IIIT Pets","dataset_url":"/dataset/oxford-iiit-pets-1","rows_in_archive":19,"metrics":["Accuracy","Top-1 Error Rate","FLOPS","PARAMS"],"first_row_in_archive_order":{"model":"EffNet-L2 (SAM)","paper_title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","paper_url":"/paper/sharpness-aware-minimization-for-efficiently-1","paper_date":"2020-10-03","arxiv_id":"2010.01412","code_links":[{"title":"davda54/sam","url":"https://github.com/davda54/sam"},{"title":"google-research/sam","url":"https://github.com/google-research/sam"},{"title":"moskomule/sam.pytorch","url":"https://github.com/moskomule/sam.pytorch"},{"title":"simon20010923/DDAMFN","url":"https://github.com/simon20010923/DDAMFN"},{"title":"ys-zong/medfair","url":"https://github.com/ys-zong/medfair"},{"title":"sayakpaul/Sharpness-Aware-Minimization-TensorFlow","url":"https://github.com/sayakpaul/Sharpness-Aware-Minimization-TensorFlow"},{"title":"wangermeng2021/Scaled-YOLOv4-tensorflow2","url":"https://github.com/wangermeng2021/Scaled-YOLOv4-tensorflow2"},{"title":"Jannoshh/simple-sam","url":"https://github.com/Jannoshh/simple-sam"},{"title":"rollovd/LookSAM","url":"https://github.com/rollovd/LookSAM"},{"title":"wangermeng2021/FastClassification","url":"https://github.com/wangermeng2021/FastClassification"},{"title":"borealisai/perturbed-forgetting","url":"https://github.com/borealisai/perturbed-forgetting"},{"title":"mhassann22/GCSAM","url":"https://github.com/mhassann22/GCSAM"},{"title":"Janus-Shiau/SAM-tf2","url":"https://github.com/Janus-Shiau/SAM-tf2"},{"title":"NiMlr/pynlqn","url":"https://github.com/NiMlr/pynlqn"},{"title":"Ashay-20/TF-SAM-Sharpness-Aware-Minimization-Implementation","url":"https://github.com/Ashay-20/TF-SAM-Sharpness-Aware-Minimization-Implementation"},{"title":"Yuheon/Sharp-Aware-Minimization","url":"https://github.com/Yuheon/Sharp-Aware-Minimization"},{"title":"denizyuret/playground","url":"https://github.com/denizyuret/playground"},{"title":"MindCode-4/code-13","url":"https://github.com/MindCode-4/code-13/tree/main/Scalable-Sharpness-Aware-Minimization"}],"syntology":{"n":20,"n_ran":15,"n_constructed":6,"n_ran_checked":13,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":6,"phrase":"15 ran (of which 6 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/sharpness-aware-minimization-for-efficiently-1#ran","syntology_url":"https://syntology.ai/paper/2010.01412","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.01412"}},"official":{"repos":["google-research/sam"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["listed","official"]}}}},{"leaderboard":"/sota/fine-grained-image-classification-on-caltech","slug":"fine-grained-image-classification-on-caltech","dataset":"Caltech-101","dataset_url":"/dataset/caltech-101","rows_in_archive":18,"metrics":["Top-1 Error Rate","Accuracy"],"first_row_in_archive_order":{"model":"VIT-L/16","paper_title":"Reduction of Class Activation Uncertainty with Background Information","paper_url":"/paper/reduction-of-class-activation-uncertainty","paper_date":"2023-05-05","arxiv_id":"2305.03238","code_links":[{"title":"dipuk0506/SpinalNet","url":"https://github.com/dipuk0506/SpinalNet"},{"title":"dipuk0506/uq","url":"https://github.com/dipuk0506/uq"}],"syntology":null}},{"leaderboard":"/sota/fine-grained-image-classification-on-food-101","slug":"fine-grained-image-classification-on-food-101","dataset":"Food-101","dataset_url":"/dataset/food-101","rows_in_archive":15,"metrics":["Accuracy","FLOPS","PARAMS","Top 1 Accuracy"],"first_row_in_archive_order":{"model":"CAP","paper_title":"Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification","paper_url":"/paper/context-aware-attentional-pooling-cap-for","paper_date":"2021-01-17","arxiv_id":"2101.06635","code_links":[{"title":"ArdhenduBehera/cap","url":"https://github.com/ArdhenduBehera/cap"}],"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/context-aware-attentional-pooling-cap-for#ran","syntology_url":"https://syntology.ai/paper/2101.06635","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.06635"}},"official":null}}},{"leaderboard":"/sota/fine-grained-image-classification-on-oxford-1","slug":"fine-grained-image-classification-on-oxford-1","dataset":"Oxford-IIIT Pet Dataset","dataset_url":"/dataset/oxford-iiit-pets","rows_in_archive":15,"metrics":["Accuracy","Top-1 Error Rate","FLOPS","PARAMS"],"first_row_in_archive_order":{"model":"OmniVec2","paper_title":"OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","paper_url":"/paper/omnivec2-a-novel-transformer-based-network","paper_date":"2024-01-01","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/fine-grained-image-classification-on-cub-200","slug":"fine-grained-image-classification-on-cub-200","dataset":"CUB-200-2011","dataset_url":"/dataset/cub-200-2011","rows_in_archive":12,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"TransFG","paper_title":"TransFG: A Transformer Architecture for Fine-grained Recognition","paper_url":"/paper/transfg-a-transformer-architecture-for-fine","paper_date":"2021-03-14","arxiv_id":"2103.07976","code_links":[{"title":"TACJu/TransFG","url":"https://github.com/TACJu/TransFG"},{"title":"skchen1993/TrangFG","url":"https://github.com/skchen1993/TrangFG"}],"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/transfg-a-transformer-architecture-for-fine#ran","syntology_url":"https://syntology.ai/paper/2103.07976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.07976"}},"official":{"repos":["TACJu/TransFG"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}}},{"leaderboard":"/sota/fine-grained-image-classification-on-compcars","slug":"fine-grained-image-classification-on-compcars","dataset":"CompCars","dataset_url":"/dataset/compcars","rows_in_archive":7,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Resnet50 + PMAL","paper_title":"Progressive Multi-task Anti-Noise Learning and Distilling Frameworks for Fine-grained Vehicle Recognition","paper_url":"/paper/progressive-multi-task-anti-noise-learning","paper_date":"2024-01-25","arxiv_id":"2401.14336","code_links":[{"title":"dichao-liu/anti-noise_fgvr","url":"https://github.com/dichao-liu/anti-noise_fgvr"}],"syntology":null}},{"leaderboard":"/sota/fine-grained-image-classification-on-bird-225","slug":"fine-grained-image-classification-on-bird-225","dataset":"Bird-225","dataset_url":"/dataset/bird","rows_in_archive":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"WideResNet-101 (Spinal FC)","paper_title":"A Comprehensive Study on Torchvision Pre-trained Models for Fine-grained Inter-species Classification","paper_url":"/paper/a-comprehensive-study-on-torchvision-pre","paper_date":"2021-10-14","arxiv_id":"2110.07097","code_links":[{"title":"dipuk0506/SpinalNet","url":"https://github.com/dipuk0506/SpinalNet"}],"syntology":null}},{"leaderboard":"/sota/fine-grained-image-classification-on-birdsnap","slug":"fine-grained-image-classification-on-birdsnap","dataset":"Birdsnap","dataset_url":"/dataset/birdsnap","rows_in_archive":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"EffNet-L2 (SAM)","paper_title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","paper_url":"/paper/sharpness-aware-minimization-for-efficiently-1","paper_date":"2020-10-03","arxiv_id":"2010.01412","code_links":[{"title":"davda54/sam","url":"https://github.com/davda54/sam"},{"title":"google-research/sam","url":"https://github.com/google-research/sam"},{"title":"moskomule/sam.pytorch","url":"https://github.com/moskomule/sam.pytorch"},{"title":"simon20010923/DDAMFN","url":"https://github.com/simon20010923/DDAMFN"},{"title":"ys-zong/medfair","url":"https://github.com/ys-zong/medfair"},{"title":"sayakpaul/Sharpness-Aware-Minimization-TensorFlow","url":"https://github.com/sayakpaul/Sharpness-Aware-Minimization-TensorFlow"},{"title":"wangermeng2021/Scaled-YOLOv4-tensorflow2","url":"https://github.com/wangermeng2021/Scaled-YOLOv4-tensorflow2"},{"title":"Jannoshh/simple-sam","url":"https://github.com/Jannoshh/simple-sam"},{"title":"rollovd/LookSAM","url":"https://github.com/rollovd/LookSAM"},{"title":"wangermeng2021/FastClassification","url":"https://github.com/wangermeng2021/FastClassification"},{"title":"borealisai/perturbed-forgetting","url":"https://github.com/borealisai/perturbed-forgetting"},{"title":"mhassann22/GCSAM","url":"https://github.com/mhassann22/GCSAM"},{"title":"Janus-Shiau/SAM-tf2","url":"https://github.com/Janus-Shiau/SAM-tf2"},{"title":"NiMlr/pynlqn","url":"https://github.com/NiMlr/pynlqn"},{"title":"Ashay-20/TF-SAM-Sharpness-Aware-Minimization-Implementation","url":"https://github.com/Ashay-20/TF-SAM-Sharpness-Aware-Minimization-Implementation"},{"title":"Yuheon/Sharp-Aware-Minimization","url":"https://github.com/Yuheon/Sharp-Aware-Minimization"},{"title":"denizyuret/playground","url":"https://github.com/denizyuret/playground"},{"title":"MindCode-4/code-13","url":"https://github.com/MindCode-4/code-13/tree/main/Scalable-Sharpness-Aware-Minimization"}],"syntology":{"n":20,"n_ran":15,"n_constructed":6,"n_ran_checked":13,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":6,"phrase":"15 ran (of which 6 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/sharpness-aware-minimization-for-efficiently-1#ran","syntology_url":"https://syntology.ai/paper/2010.01412","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.01412"}},"official":{"repos":["google-research/sam"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["listed","official"]}}}},{"leaderboard":"/sota/fine-grained-image-classification-on-sun397","slug":"fine-grained-image-classification-on-sun397","dataset":"SUN397","dataset_url":"/dataset/sun397","rows_in_archive":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"µ2Net (ViT-L/16)","paper_title":"An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems","paper_url":"/paper/an-evolutionary-approach-to-dynamic","paper_date":"2022-05-25","arxiv_id":"2205.12755","code_links":[{"title":"google-research/google-research","url":"https://github.com/google-research/google-research/tree/master/muNet"}],"syntology":null}},{"leaderboard":"/sota/fine-grained-image-classification-on-10","slug":"fine-grained-image-classification-on-10","dataset":"10 Monkey Species","dataset_url":null,"rows_in_archive":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Inception-v3 (Spinal FC)","paper_title":"A Comprehensive Study on Torchvision Pre-trained Models for Fine-grained Inter-species Classification","paper_url":"/paper/a-comprehensive-study-on-torchvision-pre","paper_date":"2021-10-14","arxiv_id":"2110.07097","code_links":[{"title":"dipuk0506/SpinalNet","url":"https://github.com/dipuk0506/SpinalNet"}],"syntology":null}},{"leaderboard":"/sota/fine-grained-image-classification-on-fruits","slug":"fine-grained-image-classification-on-fruits","dataset":"Fruits-360","dataset_url":null,"rows_in_archive":3,"metrics":["Accuracy (%)","Accuracy"],"first_row_in_archive_order":{"model":"ResNeXt-101","paper_title":"A Comprehensive Study on Torchvision Pre-trained Models for Fine-grained Inter-species Classification","paper_url":"/paper/a-comprehensive-study-on-torchvision-pre","paper_date":"2021-10-14","arxiv_id":"2110.07097","code_links":[{"title":"dipuk0506/SpinalNet","url":"https://github.com/dipuk0506/SpinalNet"}],"syntology":null}},{"leaderboard":"/sota/fine-grained-image-classification-on-foodx","slug":"fine-grained-image-classification-on-foodx","dataset":"FoodX-251","dataset_url":"/dataset/foodx-251","rows_in_archive":2,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"CSWin-L","paper_title":"Learning Multi-Subset of Classes for Fine-Grained Food Recognition","paper_url":"/paper/learning-multi-subset-of-classes-for-fine","paper_date":"2022-10-10","arxiv_id":null,"code_links":[{"title":"javierrodenas/Learning-Multi-Subset-of-Classes-for-Fine-Grained-Recognition","url":"https://github.com/javierrodenas/Learning-Multi-Subset-of-Classes-for-Fine-Grained-Recognition"}],"syntology":null}},{"leaderboard":"/sota/fine-grained-image-classification-on","slug":"fine-grained-image-classification-on","dataset":"Imbalanced CUB-200-2011","dataset_url":"/dataset/cub-200-2011","rows_in_archive":1,"metrics":["Accuracy","Average Per-Class Accuracy"],"first_row_in_archive_order":{"model":"PC-Softmax","paper_title":"Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimator","paper_url":"/paper/rethinking-softmax-with-cross-entropy-neural","paper_date":"2019-11-25","arxiv_id":"1911.10688","code_links":[{"title":"ZhenyueQin/Research-Softmax-with-Mutual-Information","url":"https://github.com/ZhenyueQin/Research-Softmax-with-Mutual-Information"}],"syntology":null}},{"leaderboard":"/sota/fine-grained-image-classification-on-1","slug":"fine-grained-image-classification-on-1","dataset":"Kuzushiji-MNIST","dataset_url":"/dataset/kuzushiji-mnist","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"VGG-5","paper_title":"ProgressiveSpinalNet architecture for FC layers","paper_url":"/paper/progressivespinalnet-architecture-for-fc","paper_date":"2021-03-21","arxiv_id":"2103.11373","code_links":[{"title":"praveenchopra/ProgressiveSpinalNet","url":"https://github.com/praveenchopra/ProgressiveSpinalNet"}],"syntology":null}},{"leaderboard":"/sota/fine-grained-image-classification-on-2","slug":"fine-grained-image-classification-on-2","dataset":"BoxCars116K","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ResNet152 + COOC","paper_title":"Fine-Grained Vehicle Classification with Unsupervised Parts Co-occurrence Learning","paper_url":"/paper/fine-grained-vehicle-classification-with","paper_date":"2019-01-23","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/fine-grained-image-classification-on-3","slug":"fine-grained-image-classification-on-3","dataset":"iNaturalist","dataset_url":"/dataset/inaturalist","rows_in_archive":1,"metrics":["Top 1 Accuracy"],"first_row_in_archive_order":{"model":"TASN","paper_title":"Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognition","paper_url":"/paper/looking-for-the-devil-in-the-details-learning","paper_date":"2019-03-14","arxiv_id":"1903.06150","code_links":[{"title":"researchmm/tasn","url":"https://github.com/researchmm/tasn"}],"syntology":null}},{"leaderboard":"/sota/fine-grained-image-classification-on-4","slug":"fine-grained-image-classification-on-4","dataset":"Herbarium 2021 Half–Earth","dataset_url":"/dataset/herbarium-2021-half-earth","rows_in_archive":1,"metrics":["Test F1 score"],"first_row_in_archive_order":{"model":"Conviformer-B","paper_title":"Conviformers: Convolutionally guided Vision Transformer","paper_url":"/paper/conviformers-convolutionally-guided-vision","paper_date":"2022-08-17","arxiv_id":"2208.08900","code_links":[{"title":"vaishnavmohit/Conviformer","url":"https://github.com/vaishnavmohit/Conviformer"}],"syntology":null}},{"leaderboard":"/sota/fine-grained-image-classification-on-5","slug":"fine-grained-image-classification-on-5","dataset":"Herbarium 2022","dataset_url":"/dataset/herbarium-2022","rows_in_archive":1,"metrics":["Test F1 score (private)"],"first_row_in_archive_order":{"model":"Conviformer-B","paper_title":"Conviformers: Convolutionally guided Vision Transformer","paper_url":"/paper/conviformers-convolutionally-guided-vision","paper_date":"2022-08-17","arxiv_id":"2208.08900","code_links":[{"title":"vaishnavmohit/Conviformer","url":"https://github.com/vaishnavmohit/Conviformer"}],"syntology":null}},{"leaderboard":"/sota/fine-grained-image-classification-on-bottles","slug":"fine-grained-image-classification-on-bottles","dataset":"Bottles","dataset_url":null,"rows_in_archive":1,"metrics":["mAP"],"first_row_in_archive_order":{"model":"PHOC descriptor + Fisher Vector Encoding","paper_title":"Fine-grained Image Classification and Retrieval by Combining Visual and Locally Pooled Textual Features","paper_url":"/paper/fine-grained-image-classification-and","paper_date":"2020-01-14","arxiv_id":"2001.04732","code_links":[{"title":"DreadPiratePsyopus/Fine_Grained_Clf","url":"https://github.com/DreadPiratePsyopus/Fine_Grained_Clf"},{"title":"AndresPMD/Fine_Grained_Clf","url":"https://github.com/AndresPMD/Fine_Grained_Clf"}],"syntology":null}},{"leaderboard":"/sota/fine-grained-image-classification-on-carflag","slug":"fine-grained-image-classification-on-carflag","dataset":"CarFlag-1532","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ResNet101-swp","paper_title":"Deep CNNs With Spatially Weighted Pooling for Fine-Grained Car Recognition","paper_url":"/paper/deep-cnns-with-spatially-weighted-pooling-for","paper_date":"2017-04-04","arxiv_id":null,"code_links":[{"title":"duongttr/SWP","url":"https://github.com/duongttr/SWP"}],"syntology":null}},{"leaderboard":"/sota/fine-grained-image-classification-on-carflag-1","slug":"fine-grained-image-classification-on-carflag-1","dataset":"CarFlag-563","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ResNet101-swp","paper_title":"Deep CNNs With Spatially Weighted Pooling for Fine-Grained Car Recognition","paper_url":"/paper/deep-cnns-with-spatially-weighted-pooling-for","paper_date":"2017-04-04","arxiv_id":null,"code_links":[{"title":"duongttr/SWP","url":"https://github.com/duongttr/SWP"}],"syntology":null}},{"leaderboard":"/sota/fine-grained-image-classification-on-con-text","slug":"fine-grained-image-classification-on-con-text","dataset":"Con-Text","dataset_url":null,"rows_in_archive":1,"metrics":["mAP"],"first_row_in_archive_order":{"model":"PHOC descriptor + Fisher Vector Encoding","paper_title":"Fine-grained Image Classification and Retrieval by Combining Visual and Locally Pooled Textual Features","paper_url":"/paper/fine-grained-image-classification-and","paper_date":"2020-01-14","arxiv_id":"2001.04732","code_links":[{"title":"DreadPiratePsyopus/Fine_Grained_Clf","url":"https://github.com/DreadPiratePsyopus/Fine_Grained_Clf"},{"title":"AndresPMD/Fine_Grained_Clf","url":"https://github.com/AndresPMD/Fine_Grained_Clf"}],"syntology":null}},{"leaderboard":"/sota/fine-grained-image-classification-on-dib-10k","slug":"fine-grained-image-classification-on-dib-10k","dataset":"DIB-10K","dataset_url":"/dataset/dib-10k","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"MetaFGNet","paper_title":"Fine-Grained Visual Categorization using Meta-Learning Optimization with Sample Selection of Auxiliary Data","paper_url":"/paper/fine-grained-visual-categorization-using-meta","paper_date":"2018-07-28","arxiv_id":"1807.10916","code_links":[{"title":"YBZh/MetaFGNet","url":"https://github.com/YBZh/MetaFGNet"},{"title":"YabinZhang1994/MetaFGNet","url":"https://github.com/YabinZhang1994/MetaFGNet"}],"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/fine-grained-visual-categorization-using-meta#ran","syntology_url":"https://syntology.ai/paper/1807.10916","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.10916"}},"official":null}}},{"leaderboard":"/sota/fine-grained-image-classification-on-emnist","slug":"fine-grained-image-classification-on-emnist","dataset":"EMNIST-Digits","dataset_url":"/dataset/emnist","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"VGG-5","paper_title":"ProgressiveSpinalNet architecture for FC layers","paper_url":"/paper/progressivespinalnet-architecture-for-fc","paper_date":"2021-03-21","arxiv_id":"2103.11373","code_links":[{"title":"praveenchopra/ProgressiveSpinalNet","url":"https://github.com/praveenchopra/ProgressiveSpinalNet"}],"syntology":null}},{"leaderboard":"/sota/fine-grained-image-classification-on-emnist-1","slug":"fine-grained-image-classification-on-emnist-1","dataset":"EMNIST-Letters","dataset_url":"/dataset/emnist","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"VGG-5","paper_title":"ProgressiveSpinalNet architecture for FC layers","paper_url":"/paper/progressivespinalnet-architecture-for-fc","paper_date":"2021-03-21","arxiv_id":"2103.11373","code_links":[{"title":"praveenchopra/ProgressiveSpinalNet","url":"https://github.com/praveenchopra/ProgressiveSpinalNet"}],"syntology":null}},{"leaderboard":"/sota/fine-grained-image-classification-on-fgvc-2","slug":"fine-grained-image-classification-on-fgvc-2","dataset":"FGVC-Aircraft","dataset_url":"/dataset/fgvc-aircraft-1","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"EnGraf-Net101 (G=4, H=1)","paper_title":"EnGraf-Net: Multiple Granularity Branch Network with Fine-Coarse Graft Grained for Classification Task","paper_url":"/paper/engraf-net-multiple-granularity-branch","paper_date":"2021-10-21","arxiv_id":null,"code_links":[{"title":"artelabsuper/engraf-net","url":"https://gitlab.com/artelabsuper/engraf-net"}],"syntology":null}},{"leaderboard":"/sota/fine-grained-image-classification-on-mnist","slug":"fine-grained-image-classification-on-mnist","dataset":"MNIST","dataset_url":"/dataset/mnist","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Vanilla FC layer only","paper_title":"ProgressiveSpinalNet architecture for FC layers","paper_url":"/paper/progressivespinalnet-architecture-for-fc","paper_date":"2021-03-21","arxiv_id":"2103.11373","code_links":[{"title":"praveenchopra/ProgressiveSpinalNet","url":"https://github.com/praveenchopra/ProgressiveSpinalNet"}],"syntology":null}},{"leaderboard":"/sota/fine-grained-image-classification-on-qmnist","slug":"fine-grained-image-classification-on-qmnist","dataset":"QMNIST","dataset_url":"/dataset/qmnist","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"VGG-5","paper_title":"ProgressiveSpinalNet architecture for FC layers","paper_url":"/paper/progressivespinalnet-architecture-for-fc","paper_date":"2021-03-21","arxiv_id":"2103.11373","code_links":[{"title":"praveenchopra/ProgressiveSpinalNet","url":"https://github.com/praveenchopra/ProgressiveSpinalNet"}],"syntology":null}},{"leaderboard":"/sota/fine-grained-image-classification-on-sop","slug":"fine-grained-image-classification-on-sop","dataset":"SOP","dataset_url":"/dataset/stanford-online-products","rows_in_archive":1,"metrics":["Recall@1"],"first_row_in_archive_order":{"model":"Assemble-ResNet-FGVC-50","paper_title":"Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network","paper_url":"/paper/compounding-the-performance-improvements-of","paper_date":"2020-01-17","arxiv_id":"2001.06268","code_links":[{"title":"clovaai/assembled-cnn","url":"https://github.com/clovaai/assembled-cnn"}],"syntology":{"n":11,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/compounding-the-performance-improvements-of#ran","syntology_url":"https://syntology.ai/paper/2001.06268","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.06268"}},"official":{"repos":["clovaai/assembled-cnn"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":8,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/fine-grained-image-classification-on-stl-10","slug":"fine-grained-image-classification-on-stl-10","dataset":"STL-10","dataset_url":"/dataset/stl-10","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Pre trained wide-resnet-101","paper_title":"ProgressiveSpinalNet architecture for FC layers","paper_url":"/paper/progressivespinalnet-architecture-for-fc","paper_date":"2021-03-21","arxiv_id":"2103.11373","code_links":[{"title":"praveenchopra/ProgressiveSpinalNet","url":"https://github.com/praveenchopra/ProgressiveSpinalNet"}],"syntology":null}}],"datasets":[{"url":"/dataset/mnist","name":"MNIST","full_name":"","num_papers_in_archive":7651},{"url":"/dataset/cub-200-2011","name":"CUB-200-2011","full_name":"Caltech-UCSD Birds-200-2011","num_papers_in_archive":2235},{"url":"/dataset/oxford-102-flower","name":"Oxford 102 Flower","full_name":"102 Category Flower Dataset","num_papers_in_archive":1307},{"url":"/dataset/stl-10","name":"STL-10","full_name":"Self-Taught Learning 10","num_papers_in_archive":1092},{"url":"/dataset/food-101","name":"Food-101","full_name":"","num_papers_in_archive":805},{"url":"/dataset/stanford-cars","name":"Stanford Cars","full_name":"","num_papers_in_archive":790},{"url":"/dataset/caltech-101","name":"Caltech-101","full_name":"","num_papers_in_archive":709},{"url":"/dataset/inaturalist","name":"iNaturalist","full_name":"","num_papers_in_archive":603},{"url":"/dataset/fgvc-aircraft-1","name":"FGVC-Aircraft","full_name":"","num_papers_in_archive":520},{"url":"/dataset/emnist","name":"EMNIST","full_name":"Extended MNIST","num_papers_in_archive":264},{"url":"/dataset/stanford-online-products","name":"Stanford Online Products","full_name":"Stanford Online Products","num_papers_in_archive":231},{"url":"/dataset/nabirds","name":"NABirds","full_name":"North America Birds","num_papers_in_archive":143},{"url":"/dataset/kuzushiji-mnist","name":"Kuzushiji-MNIST","full_name":"","num_papers_in_archive":97},{"url":"/dataset/oxford-iiit-pets","name":"Oxford-IIIT Pet Dataset","full_name":"Oxford-IIIT Pet Dataset","num_papers_in_archive":90},{"url":"/dataset/birdsnap","name":"Birdsnap","full_name":"","num_papers_in_archive":72},{"url":"/dataset/compcars","name":"CompCars","full_name":"Comprehensive Cars","num_papers_in_archive":70},{"url":"/dataset/oxford-iiit-pets-1","name":"Oxford-IIIT Pets","full_name":"","num_papers_in_archive":59},{"url":"/dataset/stanford-dogs","name":"Stanford Dogs","full_name":"Stanford Dogs","num_papers_in_archive":57},{"url":"/dataset/sun397","name":"SUN397","full_name":"SUN397","num_papers_in_archive":52},{"url":"/dataset/qmnist","name":"QMNIST","full_name":null,"num_papers_in_archive":26},{"url":"/dataset/ip102","name":"IP102","full_name":"","num_papers_in_archive":22},{"url":"/dataset/foodx-251","name":"FoodX-251","full_name":"","num_papers_in_archive":11},{"url":"/dataset/cropandweed-dataset","name":"CropAndWeed","full_name":"","num_papers_in_archive":10},{"url":"/dataset/webfg-496","name":"WebFG-496","full_name":"","num_papers_in_archive":7},{"url":"/dataset/bird","name":"BIRD","full_name":"Blocksworld Image Reasoning Dataset","num_papers_in_archive":5},{"url":"/dataset/aircraft-context-dataset","name":"Aircraft Context Dataset","full_name":"","num_papers_in_archive":3},{"url":"/dataset/rp2k","name":"RP2K","full_name":"","num_papers_in_archive":3},{"url":"/dataset/dib-10k","name":"DIB-10K","full_name":"DongNiao International Birds 10000","num_papers_in_archive":2},{"url":"/dataset/herbarium-2021-half-earth","name":"Herbarium 2021 Half–Earth","full_name":"","num_papers_in_archive":2},{"url":"/dataset/lymphomnist","name":"LymphoMNIST","full_name":"LymphoMNIST","num_papers_in_archive":2},{"url":"/dataset/apron-dataset","name":"Apron Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/cinat-birds-2021","name":"CiNAT-Birds-2021","full_name":"Cross-View iNaturalist Birds 2021","num_papers_in_archive":1},{"url":"/dataset/fgscm-52","name":"FGSCM-52","full_name":"","num_papers_in_archive":1},{"url":"/dataset/herbarium-2022","name":"Herbarium 2022","full_name":"Identify plant species of the Americas from herbarium specimens","num_papers_in_archive":1},{"url":"/dataset/inaturalist-fine-grained-geolocation","name":"iNaturalist Fine-Grained Geolocation","full_name":null,"num_papers_in_archive":1},{"url":"/dataset/orchid2024","name":"Orchid2024","full_name":"","num_papers_in_archive":1},{"url":"/dataset/spot-10","name":"SPOT-10","full_name":"Animal Pattern Benchmark Dataset for Machine Learning Algorithms","num_papers_in_archive":1},{"url":"/dataset/tsinghua-dogs","name":"Tsinghua Dogs","full_name":"","num_papers_in_archive":1},{"url":"/dataset/wikichurches","name":"WikiChurches","full_name":"","num_papers_in_archive":1},{"url":"/dataset/yfcc100m-fine-grained-geolocation","name":"YFCC100M Fine-Grained Geolocation","full_name":null,"num_papers_in_archive":1},{"url":"/dataset/corn-seeds-dataset","name":"Corn Seeds Dataset","full_name":"","num_papers_in_archive":0}],"subtasks":[{"url":"/task/displaced-people-recognition","name":"Displaced People Recognition"}],"parent_tasks":[{"url":"/task/image-classification","name":"Image Classification"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":4,"rows_per_page":100,"shown":100,"of":353,"of_with_code":200,"tagged_in_all":353,"counts":{"archive_papers_tagged":353,"with_a_code_link":200,"where_syntology_ran_a_sample":54,"not_listed_spam_title":0,"listed":353,"listed_where_code_ran":54,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":48,"every_run_a_failure_of_syntologys_instrument":6,"listed_with_a_run_with_no_instrument_failure":48,"listed_every_run_a_failure_of_syntologys_instrument":6,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/efficientnet-rethinking-model-scaling-for","slug":"efficientnet-rethinking-model-scaling-for","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","date":"2019-05-28","arxiv_id":"1905.11946","repositories_listed":144,"syntology":{"n":302,"n_ran":198,"n_constructed":73,"n_ran_checked":157,"n_instrument":41,"n_unverified":104,"n_honours":26,"n_violates":2,"n_no_contract":129,"n_pointer_only":113,"phrase":"198 ran (of which 73 constructed an object rather than computing a result; 157 with no instrument failure: 26 honoured, 2 violated, 129 with no contract checked; 41 where Syntology's instrument failed) · 104 unverified","sample_list":"/paper/efficientnet-rethinking-model-scaling-for#ran","syntology_url":"https://syntology.ai/paper/1905.11946","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.11946"}},"official":{"repos":["tensorflow/tpu"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/training-data-efficient-image-transformers","slug":"training-data-efficient-image-transformers","title":"Training data-efficient image transformers & distillation through attention","date":"2020-12-23","arxiv_id":"2012.12877","repositories_listed":40,"syntology":{"n":19,"n_ran":12,"n_constructed":1,"n_ran_checked":9,"n_instrument":3,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":3,"phrase":"12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/training-data-efficient-image-transformers#ran","syntology_url":"https://syntology.ai/paper/2012.12877","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.12877"}},"official":{"repos":["facebookresearch/deit"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/autoaugment-learning-augmentation-policies","slug":"autoaugment-learning-augmentation-policies","title":"AutoAugment: Learning Augmentation Policies from Data","date":"2018-05-24","arxiv_id":"1805.09501","repositories_listed":33,"syntology":{"n":43,"n_ran":25,"n_constructed":0,"n_ran_checked":22,"n_instrument":3,"n_unverified":18,"n_honours":1,"n_violates":2,"n_no_contract":19,"n_pointer_only":4,"phrase":"25 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 1 honoured, 2 violated, 19 with no contract checked; 3 where Syntology's instrument failed) · 18 unverified","sample_list":"/paper/autoaugment-learning-augmentation-policies#ran","syntology_url":"https://syntology.ai/paper/1805.09501","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.09501"}},"official":{"repos":["tensorflow/models"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/dinov2-learning-robust-visual-features","slug":"dinov2-learning-robust-visual-features","title":"DINOv2: Learning Robust Visual Features without Supervision","date":"2023-04-14","arxiv_id":"2304.07193","repositories_listed":26,"syntology":{"n":46,"n_ran":39,"n_constructed":13,"n_ran_checked":32,"n_instrument":7,"n_unverified":7,"n_honours":2,"n_violates":0,"n_no_contract":30,"n_pointer_only":12,"phrase":"39 ran (of which 13 constructed an object rather than computing a result; 32 with no instrument failure: 2 honoured, 0 violated, 30 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/dinov2-learning-robust-visual-features#ran","syntology_url":"https://syntology.ai/paper/2304.07193","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.07193"}},"official":{"repos":["facebookresearch/dinov2"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/resmlp-feedforward-networks-for-image","slug":"resmlp-feedforward-networks-for-image","title":"ResMLP: Feedforward networks for image classification with data-efficient training","date":"2021-05-07","arxiv_id":"2105.03404","repositories_listed":19,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/resmlp-feedforward-networks-for-image#ran","syntology_url":"https://syntology.ai/paper/2105.03404","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.03404"}},"official":{"repos":["facebookresearch/deit"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/sharpness-aware-minimization-for-efficiently-1","slug":"sharpness-aware-minimization-for-efficiently-1","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","date":"2020-10-03","arxiv_id":"2010.01412","repositories_listed":18,"syntology":{"n":20,"n_ran":15,"n_constructed":6,"n_ran_checked":13,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":6,"phrase":"15 ran (of which 6 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/sharpness-aware-minimization-for-efficiently-1#ran","syntology_url":"https://syntology.ai/paper/2010.01412","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.01412"}},"official":{"repos":["google-research/sam"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/resnet-strikes-back-an-improved-training","slug":"resnet-strikes-back-an-improved-training","title":"ResNet strikes back: An improved training procedure in timm","date":"2021-10-01","arxiv_id":"2110.00476","repositories_listed":14,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/resnet-strikes-back-an-improved-training#ran","syntology_url":"https://syntology.ai/paper/2110.00476","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.00476"}},"official":{"repos":["rwightman/pytorch-image-models"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/gpipe-efficient-training-of-giant-neural","slug":"gpipe-efficient-training-of-giant-neural","title":"GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism","date":"2018-11-16","arxiv_id":"1811.06965","repositories_listed":13,"syntology":{"n":25,"n_ran":20,"n_constructed":0,"n_ran_checked":19,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":19,"n_pointer_only":16,"phrase":"20 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/gpipe-efficient-training-of-giant-neural#ran","syntology_url":"https://syntology.ai/paper/1811.06965","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.06965"}},"official":null}},{"url":"/paper/transformer-in-transformer","slug":"transformer-in-transformer","title":"Transformer in Transformer","date":"2021-02-27","arxiv_id":"2103.00112","repositories_listed":12,"syntology":{"n":24,"n_ran":16,"n_constructed":12,"n_ran_checked":15,"n_instrument":1,"n_unverified":8,"n_honours":1,"n_violates":1,"n_no_contract":13,"n_pointer_only":5,"phrase":"16 ran (of which 12 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 1 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/transformer-in-transformer#ran","syntology_url":"https://syntology.ai/paper/2103.00112","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.00112"}},"official":{"repos":["huawei-noah/CV-backbones"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/learning-to-navigate-for-fine-grained","slug":"learning-to-navigate-for-fine-grained","title":"Learning to Navigate for Fine-grained Classification","date":"2018-09-02","arxiv_id":"1809.00287","repositories_listed":12,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-to-navigate-for-fine-grained#ran","syntology_url":"https://syntology.ai/paper/1809.00287","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.00287"}},"official":{"repos":["yangze0930/NTS-Net"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/escaping-the-big-data-paradigm-with-compact","slug":"escaping-the-big-data-paradigm-with-compact","title":"Escaping the Big Data Paradigm with Compact Transformers","date":"2021-04-12","arxiv_id":"2104.05704","repositories_listed":9,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/escaping-the-big-data-paradigm-with-compact#ran","syntology_url":"https://syntology.ai/paper/2104.05704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.05704"}},"official":{"repos":["SHI-Labs/Compact-Transformers"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/large-scale-learning-of-general-visual","slug":"large-scale-learning-of-general-visual","title":"Big Transfer (BiT): General Visual Representation Learning","date":"2019-12-24","arxiv_id":"1912.11370","repositories_listed":9,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/large-scale-learning-of-general-visual#ran","syntology_url":"https://syntology.ai/paper/1912.11370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.11370"}},"official":{"repos":["google-research/big_transfer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/three-things-everyone-should-know-about","slug":"three-things-everyone-should-know-about","title":"Three things everyone should know about Vision Transformers","date":"2022-03-18","arxiv_id":"2203.09795","repositories_listed":8,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/three-things-everyone-should-know-about#ran","syntology_url":"https://syntology.ai/paper/2203.09795","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.09795"}},"official":{"repos":["facebookresearch/deit"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/gradient-centralization-a-new-optimization","slug":"gradient-centralization-a-new-optimization","title":"Gradient Centralization: A New Optimization Technique for Deep Neural Networks","date":"2020-04-03","arxiv_id":"2004.01461","repositories_listed":8,"syntology":{"n":29,"n_ran":18,"n_constructed":0,"n_ran_checked":17,"n_instrument":1,"n_unverified":11,"n_honours":1,"n_violates":0,"n_no_contract":16,"n_pointer_only":3,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 1 honoured, 0 violated, 16 with no contract checked; 1 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/gradient-centralization-a-new-optimization#ran","syntology_url":"https://syntology.ai/paper/2004.01461","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.01461"}},"official":{"repos":["Yonghongwei/Gradient-Centralization"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/unlabeled-samples-generated-by-gan-improve","slug":"unlabeled-samples-generated-by-gan-improve","title":"Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro","date":"2017-01-26","arxiv_id":"1701.07717","repositories_listed":8,"syntology":null},{"url":"/paper/three-branch-and-mutil-scale-learning-for","slug":"three-branch-and-mutil-scale-learning-for","title":"Multi-branch and Multi-scale Attention Learning for Fine-Grained Visual Categorization","date":"2020-03-20","arxiv_id":"2003.09150","repositories_listed":6,"syntology":null},{"url":"/paper/imagenet-21k-pretraining-for-the-masses","slug":"imagenet-21k-pretraining-for-the-masses","title":"ImageNet-21K Pretraining for the Masses","date":"2021-04-22","arxiv_id":"2104.10972","repositories_listed":5,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/imagenet-21k-pretraining-for-the-masses#ran","syntology_url":"https://syntology.ai/paper/2104.10972","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.10972"}},"official":{"repos":["Alibaba-MIIL/ImageNet21K"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/scaling-up-visual-and-vision-language","slug":"scaling-up-visual-and-vision-language","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","date":"2021-02-11","arxiv_id":"2102.05918","repositories_listed":5,"syntology":{"n":10,"n_ran":8,"n_constructed":6,"n_ran_checked":7,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"phrase":"8 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/scaling-up-visual-and-vision-language#ran","syntology_url":"https://syntology.ai/paper/2102.05918","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.05918"}},"official":null}},{"url":"/paper/fine-grained-visual-classification-via","slug":"fine-grained-visual-classification-via","title":"Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches","date":"2020-03-08","arxiv_id":"2003.03836","repositories_listed":5,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/fine-grained-visual-classification-via#ran","syntology_url":"https://syntology.ai/paper/2003.03836","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.03836"}},"official":{"repos":["PRIS-CV/PMG-Progressive-Multi-Granularity-Training","RuoyiDu/PMG-Progressive-Multi-Granularity-Training"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/your-diffusion-model-is-secretly-a-zero-shot","slug":"your-diffusion-model-is-secretly-a-zero-shot","title":"Your Diffusion Model is Secretly a Zero-Shot Classifier","date":"2023-03-28","arxiv_id":"2303.16203","repositories_listed":4,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/your-diffusion-model-is-secretly-a-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2303.16203","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16203"}},"official":{"repos":["diffusion-classifier/diffusion-classifier"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/with-a-little-help-from-my-friends-nearest","slug":"with-a-little-help-from-my-friends-nearest","title":"With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations","date":"2021-04-29","arxiv_id":"2104.14548","repositories_listed":4,"syntology":{"n":5,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/with-a-little-help-from-my-friends-nearest#ran","syntology_url":"https://syntology.ai/paper/2104.14548","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.14548"}},"official":null}},{"url":"/paper/presence-only-geographical-priors-for-fine","slug":"presence-only-geographical-priors-for-fine","title":"Presence-Only Geographical Priors for Fine-Grained Image Classification","date":"2019-06-12","arxiv_id":"1906.05272","repositories_listed":4,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/presence-only-geographical-priors-for-fine#ran","syntology_url":"https://syntology.ai/paper/1906.05272","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.05272"}},"official":null}},{"url":"/paper/see-better-before-looking-closer-weakly","slug":"see-better-before-looking-closer-weakly","title":"See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification","date":"2019-01-26","arxiv_id":"1901.09891","repositories_listed":4,"syntology":null},{"url":"/paper/towards-faster-training-of-global-covariance","slug":"towards-faster-training-of-global-covariance","title":"Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalization","date":"2017-12-04","arxiv_id":"1712.01034","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-faster-training-of-global-covariance#ran","syntology_url":"https://syntology.ai/paper/1712.01034","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.01034"}},"official":{"repos":["jiangtaoxie/fast-MPN-COV"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/bilinear-cnns-for-fine-grained-visual","slug":"bilinear-cnns-for-fine-grained-visual","title":"Bilinear CNNs for Fine-grained Visual Recognition","date":"2015-04-29","arxiv_id":"1504.07889","repositories_listed":4,"syntology":null},{"url":"/paper/densenets-reloaded-paradigm-shift-beyond","slug":"densenets-reloaded-paradigm-shift-beyond","title":"DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs","date":"2024-03-28","arxiv_id":"2403.19588","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/densenets-reloaded-paradigm-shift-beyond#ran","syntology_url":"https://syntology.ai/paper/2403.19588","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19588"}},"official":{"repos":["huggingface/pytorch-image-models","naver-ai/rdnet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/spinalnet-deep-neural-network-with-gradual-1","slug":"spinalnet-deep-neural-network-with-gradual-1","title":"SpinalNet: Deep Neural Network with Gradual Input","date":"2020-07-07","arxiv_id":"2007.03347","repositories_listed":3,"syntology":null},{"url":"/paper/proxy-anchor-loss-for-deep-metric-learning","slug":"proxy-anchor-loss-for-deep-metric-learning","title":"Proxy Anchor Loss for Deep Metric Learning","date":"2020-03-31","arxiv_id":"2003.13911","repositories_listed":3,"syntology":null},{"url":"/paper/tresnet-high-performance-gpu-dedicated","slug":"tresnet-high-performance-gpu-dedicated","title":"TResNet: High Performance GPU-Dedicated Architecture","date":"2020-03-30","arxiv_id":"2003.13630","repositories_listed":3,"syntology":null},{"url":"/paper/the-devil-is-in-the-channels-mutual-channel","slug":"the-devil-is-in-the-channels-mutual-channel","title":"The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification","date":"2020-02-11","arxiv_id":"2002.04264","repositories_listed":3,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/the-devil-is-in-the-channels-mutual-channel#ran","syntology_url":"https://syntology.ai/paper/2002.04264","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.04264"}},"official":{"repos":["dongliangchang/Mutual-Channel-Loss"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/are-these-birds-similar-learning-branched","slug":"are-these-birds-similar-learning-branched","title":"Are These Birds Similar: Learning Branched Networks for Fine-grained Representations","date":"2020-01-16","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/fixing-the-train-test-resolution-discrepancy","slug":"fixing-the-train-test-resolution-discrepancy","title":"Fixing the train-test resolution discrepancy","date":"2019-06-14","arxiv_id":"1906.06423","repositories_listed":3,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/fixing-the-train-test-resolution-discrepancy#ran","syntology_url":"https://syntology.ai/paper/1906.06423","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.06423"}},"official":{"repos":["facebookresearch/FixRes"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/learning-multi-attention-convolutional-neural","slug":"learning-multi-attention-convolutional-neural","title":"Learning Multi-Attention Convolutional Neural Network for Fine-Grained Image Recognition","date":"2017-10-01","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/a-large-scale-car-dataset-for-fine-grained","slug":"a-large-scale-car-dataset-for-fine-grained","title":"A Large-Scale Car Dataset for Fine-Grained Categorization and Verification","date":"2015-06-30","arxiv_id":"1506.08959","repositories_listed":3,"syntology":null},{"url":"/paper/advisingnets-learning-to-distinguish-correct","slug":"advisingnets-learning-to-distinguish-correct","title":"PCNN: Probable-Class Nearest-Neighbor Explanations Improve Fine-Grained Image Classification Accuracy for AIs and Humans","date":"2023-08-25","arxiv_id":"2308.13651","repositories_listed":2,"syntology":null},{"url":"/paper/reduction-of-class-activation-uncertainty","slug":"reduction-of-class-activation-uncertainty","title":"Reduction of Class Activation Uncertainty with Background Information","date":"2023-05-05","arxiv_id":"2305.03238","repositories_listed":2,"syntology":null},{"url":"/paper/take-5-interpretable-image-classification","slug":"take-5-interpretable-image-classification","title":"Take 5: Interpretable Image Classification with a Handful of Features","date":"2023-03-23","arxiv_id":"2303.13166","repositories_listed":2,"syntology":null},{"url":"/paper/learn-from-each-other-to-classify-better","slug":"learn-from-each-other-to-classify-better","title":"Learn from Each Other to Classify Better: Cross-layer Mutual Attention Learning for Fine-grained Visual Classification","date":"2023-03-22","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/the-cropandweed-dataset-a-multi-modal","slug":"the-cropandweed-dataset-a-multi-modal","title":"The CropAndWeed Dataset: A Multi-Modal Learning Approach for Efficient Crop and Weed Manipulation","date":"2023-01-06","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/bamboo-building-mega-scale-vision-dataset","slug":"bamboo-building-mega-scale-vision-dataset","title":"Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy","date":"2022-03-15","arxiv_id":"2203.07845","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bamboo-building-mega-scale-vision-dataset#ran","syntology_url":"https://syntology.ai/paper/2203.07845","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.07845"}},"official":{"repos":["davidzhangyuanhan/bamboo","zhangyuanhan-ai/bamboo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/metaformer-a-unified-meta-framework-for-fine","slug":"metaformer-a-unified-meta-framework-for-fine","title":"MetaFormer: A Unified Meta Framework for Fine-Grained Recognition","date":"2022-03-05","arxiv_id":"2203.02751","repositories_listed":2,"syntology":{"n":14,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/metaformer-a-unified-meta-framework-for-fine#ran","syntology_url":"https://syntology.ai/paper/2203.02751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.02751"}},"official":{"repos":["dqshuai/metaformer"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/dataset-condensation-with-contrastive-signals","slug":"dataset-condensation-with-contrastive-signals","title":"Dataset Condensation with Contrastive Signals","date":"2022-02-07","arxiv_id":"2202.02916","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dataset-condensation-with-contrastive-signals#ran","syntology_url":"https://syntology.ai/paper/2202.02916","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.02916"}},"official":{"repos":["saehyung-lee/dcc"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/revisiting-weakly-supervised-pre-training-of","slug":"revisiting-weakly-supervised-pre-training-of","title":"Revisiting Weakly Supervised Pre-Training of Visual Perception Models","date":"2022-01-20","arxiv_id":"2201.08371","repositories_listed":2,"syntology":null},{"url":"/paper/a-simple-episodic-linear-probe-improves","slug":"a-simple-episodic-linear-probe-improves","title":"A Simple Episodic Linear Probe Improves Visual Recognition in the Wild","date":"2022-01-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/self-supervised-learning-by-estimating-twin-1","slug":"self-supervised-learning-by-estimating-twin-1","title":"Self-Supervised Learning by Estimating Twin Class Distributions","date":"2021-10-14","arxiv_id":"2110.07402","repositories_listed":2,"syntology":{"n":15,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":6,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/self-supervised-learning-by-estimating-twin-1#ran","syntology_url":"https://syntology.ai/paper/2110.07402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.07402"}},"official":{"repos":["bytedance/TWIST"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/autoformer-searching-transformers-for-visual","slug":"autoformer-searching-transformers-for-visual","title":"AutoFormer: Searching Transformers for Visual Recognition","date":"2021-07-01","arxiv_id":"2107.00651","repositories_listed":2,"syntology":null},{"url":"/paper/when-vision-transformers-outperform-resnets","slug":"when-vision-transformers-outperform-resnets","title":"When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations","date":"2021-06-03","arxiv_id":"2106.01548","repositories_listed":2,"syntology":null},{"url":"/paper/transfg-a-transformer-architecture-for-fine","slug":"transfg-a-transformer-architecture-for-fine","title":"TransFG: A Transformer Architecture for Fine-grained Recognition","date":"2021-03-14","arxiv_id":"2103.07976","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/transfg-a-transformer-architecture-for-fine#ran","syntology_url":"https://syntology.ai/paper/2103.07976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.07976"}},"official":{"repos":["TACJu/TransFG"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/fine-grained-visual-classification-via-1","slug":"fine-grained-visual-classification-via-1","title":"Fine-Grained Visual Classification via Simultaneously Learning of Multi-regional Multi-grained Features","date":"2021-01-31","arxiv_id":"2102.00367","repositories_listed":2,"syntology":null},{"url":"/paper/snapmix-semantically-proportional-mixing-for","slug":"snapmix-semantically-proportional-mixing-for","title":"SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data","date":"2020-12-09","arxiv_id":"2012.04846","repositories_listed":2,"syntology":null},{"url":"/paper/concept-learners-for-generalizable-few-shot","slug":"concept-learners-for-generalizable-few-shot","title":"Concept Learners for Few-Shot Learning","date":"2020-07-14","arxiv_id":"2007.07375","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/concept-learners-for-generalizable-few-shot#ran","syntology_url":"https://syntology.ai/paper/2007.07375","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.07375"}},"official":{"repos":["snap-stanford/comet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/learning-semantically-enhanced-feature-for","slug":"learning-semantically-enhanced-feature-for","title":"Learning Semantically Enhanced Feature for Fine-Grained Image Classification","date":"2020-06-24","arxiv_id":"2006.13457","repositories_listed":2,"syntology":null},{"url":"/paper/neural-architecture-transfer","slug":"neural-architecture-transfer","title":"Neural Architecture Transfer","date":"2020-05-12","arxiv_id":"2005.05859","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/neural-architecture-transfer#ran","syntology_url":"https://syntology.ai/paper/2005.05859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.05859"}},"official":{"repos":["human-analysis/neural-architecture-transfer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/look-into-object-self-supervised-structure","slug":"look-into-object-self-supervised-structure","title":"Look-into-Object: Self-supervised Structure Modeling for Object Recognition","date":"2020-03-31","arxiv_id":"2003.14142","repositories_listed":2,"syntology":null},{"url":"/paper/fine-grained-image-classification-and","slug":"fine-grained-image-classification-and","title":"Fine-grained Image Classification and Retrieval by Combining Visual and Locally Pooled Textual Features","date":"2020-01-14","arxiv_id":"2001.04732","repositories_listed":2,"syntology":null},{"url":"/paper/attention-convolutional-binary-neural-tree","slug":"attention-convolutional-binary-neural-tree","title":"Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization","date":"2019-09-25","arxiv_id":"1909.11378","repositories_listed":2,"syntology":null},{"url":"/paper/classification-specific-parts-for-improving","slug":"classification-specific-parts-for-improving","title":"Classification-Specific Parts for Improving Fine-Grained Visual Categorization","date":"2019-09-16","arxiv_id":"1909.07075","repositories_listed":2,"syntology":null},{"url":"/paper/destruction-and-construction-learning-for","slug":"destruction-and-construction-learning-for","title":"Destruction and Construction Learning for Fine-Grained Image Recognition","date":"2019-06-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/evaluation-of-output-embeddings-for-fine","slug":"evaluation-of-output-embeddings-for-fine","title":"Evaluation of Output Embeddings for Fine-Grained Image Classification","date":"2014-09-30","arxiv_id":"1409.8403","repositories_listed":2,"syntology":null},{"url":"/paper/hierarchical-mask-enhanced-dual","slug":"hierarchical-mask-enhanced-dual","title":"Hierarchical Mask-Enhanced Dual Reconstruction Network for Few-Shot Fine-Grained Image Classification","date":"2025-06-25","arxiv_id":"2506.20263","repositories_listed":1,"syntology":null},{"url":"/paper/ds-fusionnet-dynamic-dual-stream-fusion-with","slug":"ds-fusionnet-dynamic-dual-stream-fusion-with","title":"DS_FusionNet: Dynamic Dual-Stream Fusion with Bidirectional Knowledge Distillation for Plant Disease Recognition","date":"2025-04-29","arxiv_id":"2504.20948","repositories_listed":1,"syntology":null},{"url":"/paper/visual-rft-visual-reinforcement-fine-tuning","slug":"visual-rft-visual-reinforcement-fine-tuning","title":"Visual-RFT: Visual Reinforcement Fine-Tuning","date":"2025-03-03","arxiv_id":"2503.01785","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/visual-rft-visual-reinforcement-fine-tuning#ran","syntology_url":"https://syntology.ai/paper/2503.01785","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.01785"}},"official":{"repos":["liuziyu77/visual-rft"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/an-attention-locating-algorithm-for","slug":"an-attention-locating-algorithm-for","title":"An Attention-Locating Algorithm for Eliminating Background Effects in Fine-grained Visual Classification","date":"2025-01-28","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/prompt-cam-a-simpler-interpretable","slug":"prompt-cam-a-simpler-interpretable","title":"Prompt-CAM: A Simpler Interpretable Transformer for Fine-Grained Analysis","date":"2025-01-16","arxiv_id":"2501.09333","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/prompt-cam-a-simpler-interpretable#ran","syntology_url":"https://syntology.ai/paper/2501.09333","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.09333"}},"official":null}},{"url":"/paper/universal-fine-grained-visual-categorization","slug":"universal-fine-grained-visual-categorization","title":"Universal Fine-grained Visual Categorization by Concept Guided Learning","date":"2025-01-06","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/vision-mamba-distillation-for-low-resolution","slug":"vision-mamba-distillation-for-low-resolution","title":"Vision Mamba Distillation for Low-resolution Fine-grained Image Classification","date":"2024-11-27","arxiv_id":"2411.17980","repositories_listed":1,"syntology":null},{"url":"/paper/interweaving-insights-high-order-feature","slug":"interweaving-insights-high-order-feature","title":"Interweaving Insights: High-Order Feature Interaction for Fine-Grained Visual Recognition","date":"2024-10-20","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/divshift-exploring-domain-specific","slug":"divshift-exploring-domain-specific","title":"DivShift: Exploring Domain-Specific Distribution Shifts in Large-Scale, Volunteer-Collected Biodiversity Datasets","date":"2024-10-17","arxiv_id":"2410.19816","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":1,"n_ran_checked":2,"n_instrument":5,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/divshift-exploring-domain-specific#ran","syntology_url":"https://syntology.ai/paper/2410.19816","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.19816"}},"official":{"repos":["moiexpositoalonsolab/DivShift"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/jpeg-inspired-deep-learning","slug":"jpeg-inspired-deep-learning","title":"JPEG Inspired Deep Learning","date":"2024-10-09","arxiv_id":"2410.07081","repositories_listed":1,"syntology":null},{"url":"/paper/generating-binary-species-range-maps","slug":"generating-binary-species-range-maps","title":"Generating Binary Species Range Maps","date":"2024-08-28","arxiv_id":"2408.15956","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/generating-binary-species-range-maps#ran","syntology_url":"https://syntology.ai/paper/2408.15956","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.15956"}},"official":{"repos":["filipgdorm/binary_range_maps"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/extremely-fine-grained-visual-classification","slug":"extremely-fine-grained-visual-classification","title":"Extremely Fine-Grained Visual Classification over Resembling Glyphs in the Wild","date":"2024-08-25","arxiv_id":"2408.13774","repositories_listed":1,"syntology":null},{"url":"/paper/multi-granularity-part-sampling-attention-for","slug":"multi-granularity-part-sampling-attention-for","title":"Multi-Granularity Part Sampling Attention for Fine-Grained Visual Classification","date":"2024-08-16","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/orchid2024-a-cultivar-level-dataset-and","slug":"orchid2024-a-cultivar-level-dataset-and","title":"Orchid2024: A cultivar-level dataset and methodology for fine-grained classification of Chinese Cymbidium Orchids","date":"2024-08-13","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/token-compensator-altering-inference-cost-of","slug":"token-compensator-altering-inference-cost-of","title":"Token Compensator: Altering Inference Cost of Vision Transformer without Re-Tuning","date":"2024-08-13","arxiv_id":"2408.06798","repositories_listed":1,"syntology":null},{"url":"/paper/exploration-of-class-center-for-fine-grained","slug":"exploration-of-class-center-for-fine-grained","title":"Exploration of Class Center for Fine-Grained Visual Classification","date":"2024-07-05","arxiv_id":"2407.04243","repositories_listed":1,"syntology":null},{"url":"/paper/pdiscoformer-relaxing-part-discovery","slug":"pdiscoformer-relaxing-part-discovery","title":"PDiscoFormer: Relaxing Part Discovery Constraints with Vision Transformers","date":"2024-07-05","arxiv_id":"2407.04538","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pdiscoformer-relaxing-part-discovery#ran","syntology_url":"https://syntology.ai/paper/2407.04538","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04538"}},"official":{"repos":["ananthu-aniraj/pdiscoformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/extract-more-from-less-efficient-fine-grained","slug":"extract-more-from-less-efficient-fine-grained","title":"Extract More from Less: Efficient Fine-Grained Visual Recognition in Low-Data Regimes","date":"2024-06-28","arxiv_id":"2406.19814","repositories_listed":1,"syntology":null},{"url":"/paper/advancing-fine-grained-classification-by","slug":"advancing-fine-grained-classification-by","title":"Advancing Fine-Grained Classification by Structure and Subject Preserving Augmentation","date":"2024-06-20","arxiv_id":"2406.14551","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/advancing-fine-grained-classification-by#ran","syntology_url":"https://syntology.ai/paper/2406.14551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14551"}},"official":{"repos":["eyalmichaeli/saspa-aug"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/denoisereid-denoising-model-for","slug":"denoisereid-denoising-model-for","title":"DenoiseRep: Denoising Model for Representation Learning","date":"2024-06-13","arxiv_id":"2406.08773","repositories_listed":1,"syntology":{"n":22,"n_ran":17,"n_constructed":2,"n_ran_checked":13,"n_instrument":4,"n_unverified":5,"n_honours":6,"n_violates":2,"n_no_contract":5,"n_pointer_only":6,"phrase":"17 ran (of which 2 constructed an object rather than computing a result; 13 with no instrument failure: 6 honoured, 2 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/denoisereid-denoising-model-for#ran","syntology_url":"https://syntology.ai/paper/2406.08773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08773"}},"official":{"repos":["wangguanan/denoiserep"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":2,"n_ran_no_instrument_failure":13,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/few-shot-classification-of-interactive","slug":"few-shot-classification-of-interactive","title":"Few-Shot Classification of Interactive Activities of Daily Living (InteractADL)","date":"2024-06-03","arxiv_id":"2406.01662","repositories_listed":1,"syntology":null},{"url":"/paper/premonition-using-generative-models-to","slug":"premonition-using-generative-models-to","title":"Premonition: Using Generative Models to Preempt Future Data Changes in Continual Learning","date":"2024-03-12","arxiv_id":"2403.07356","repositories_listed":1,"syntology":null},{"url":"/paper/invariant-test-time-adaptation-for-vision","slug":"invariant-test-time-adaptation-for-vision","title":"Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model","date":"2024-03-01","arxiv_id":"2403.00376","repositories_listed":1,"syntology":null},{"url":"/paper/progressive-multi-task-anti-noise-learning","slug":"progressive-multi-task-anti-noise-learning","title":"Progressive Multi-task Anti-Noise Learning and Distilling Frameworks for Fine-grained Vehicle Recognition","date":"2024-01-25","arxiv_id":"2401.14336","repositories_listed":1,"syntology":null},{"url":"/paper/improved-zero-shot-classification-by-adapting","slug":"improved-zero-shot-classification-by-adapting","title":"Improved Zero-Shot Classification by Adapting VLMs with Text Descriptions","date":"2024-01-04","arxiv_id":"2401.02460","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/improved-zero-shot-classification-by-adapting#ran","syntology_url":"https://syntology.ai/paper/2401.02460","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.02460"}},"official":{"repos":["cvl-umass/adaptclipzs"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/masked-image-modeling-via-dynamic-token","slug":"masked-image-modeling-via-dynamic-token","title":"Morphing Tokens Draw Strong Masked Image Models","date":"2023-12-30","arxiv_id":"2401.00254","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 3 unverified","sample_list":"/paper/masked-image-modeling-via-dynamic-token#ran","syntology_url":"https://syntology.ai/paper/2401.00254","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.00254"}},"official":{"repos":["naver-ai/dtm"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/roll-with-the-punches-expansion-and-shrinkage","slug":"roll-with-the-punches-expansion-and-shrinkage","title":"Roll With the Punches: Expansion and Shrinkage of Soft Label Selection for Semi-supervised Fine-Grained Learning","date":"2023-12-19","arxiv_id":"2312.12237","repositories_listed":1,"syntology":null},{"url":"/paper/human-in-the-loop-estimation-of-cluster-count","slug":"human-in-the-loop-estimation-of-cluster-count","title":"Human-in-the-Loop Visual Re-ID for Population Size Estimation","date":"2023-12-08","arxiv_id":"2312.05287","repositories_listed":1,"syntology":null},{"url":"/paper/good-questions-help-zero-shot-image-reasoning","slug":"good-questions-help-zero-shot-image-reasoning","title":"Good Questions Help Zero-Shot Image Reasoning","date":"2023-12-04","arxiv_id":"2312.01598","repositories_listed":1,"syntology":null},{"url":"/paper/gift-generative-interpretable-fine-tuning","slug":"gift-generative-interpretable-fine-tuning","title":"Generative Parameter-Efficient Fine-Tuning","date":"2023-12-01","arxiv_id":"2312.00700","repositories_listed":1,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":6,"n_instrument":6,"n_unverified":4,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":10,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/gift-generative-interpretable-fine-tuning#ran","syntology_url":"https://syntology.ai/paper/2312.00700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.00700"}},"official":{"repos":["savadikarc/gift"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/meta-co-training-two-views-are-better-than","slug":"meta-co-training-two-views-are-better-than","title":"Meta Co-Training: Two Views are Better than One","date":"2023-11-29","arxiv_id":"2311.18083","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/meta-co-training-two-views-are-better-than#ran","syntology_url":"https://syntology.ai/paper/2311.18083","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.18083"}},"official":{"repos":["jayrothenberger/meta-co-training"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-simple-interpretable-transformer-for-fine","slug":"a-simple-interpretable-transformer-for-fine","title":"A Simple Interpretable Transformer for Fine-Grained Image Classification and Analysis","date":"2023-11-07","arxiv_id":"2311.04157","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-simple-interpretable-transformer-for-fine#ran","syntology_url":"https://syntology.ai/paper/2311.04157","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.04157"}},"official":{"repos":["imageomics/intr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/birdsat-cross-view-contrastive-masked","slug":"birdsat-cross-view-contrastive-masked","title":"BirdSAT: Cross-View Contrastive Masked Autoencoders for Bird Species Classification and Mapping","date":"2023-10-29","arxiv_id":"2310.19168","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/birdsat-cross-view-contrastive-masked#ran","syntology_url":"https://syntology.ai/paper/2310.19168","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.19168"}},"official":{"repos":["mvrl/birdsat"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/longer-range-contextualized-masked","slug":"longer-range-contextualized-masked","title":"Learning with Unmasked Tokens Drives Stronger Vision Learners","date":"2023-10-20","arxiv_id":"2310.13593","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/longer-range-contextualized-masked#ran","syntology_url":"https://syntology.ai/paper/2310.13593","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.13593"}},"official":{"repos":["naver-ai/lut"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/parameter-efficient-long-tailed-recognition","slug":"parameter-efficient-long-tailed-recognition","title":"Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts","date":"2023-09-18","arxiv_id":"2309.10019","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":8,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/parameter-efficient-long-tailed-recognition#ran","syntology_url":"https://syntology.ai/paper/2309.10019","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.10019"}},"official":{"repos":["shijxcs/lift"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/masking-strategies-for-background-bias","slug":"masking-strategies-for-background-bias","title":"Masking Strategies for Background Bias Removal in Computer Vision Models","date":"2023-08-23","arxiv_id":"2308.12127","repositories_listed":1,"syntology":null},{"url":"/paper/multiscale-patch-based-feature-graphs-for","slug":"multiscale-patch-based-feature-graphs-for","title":"Multiscale patch-based feature graphs for image classification","date":"2023-08-08","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/task-oriented-channel-attention-for-fine","slug":"task-oriented-channel-attention-for-fine","title":"Task-Oriented Channel Attention for Fine-Grained Few-Shot Classification","date":"2023-07-28","arxiv_id":"2308.00093","repositories_listed":1,"syntology":null},{"url":"/paper/generating-image-specific-text-improves-fine","slug":"generating-image-specific-text-improves-fine","title":"GIST: Generating Image-Specific Text for Fine-grained Object Classification","date":"2023-07-21","arxiv_id":"2307.11315","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-models-beat-gans-on-image","slug":"diffusion-models-beat-gans-on-image","title":"Diffusion Models Beat GANs on Image Classification","date":"2023-07-17","arxiv_id":"2307.08702","repositories_listed":1,"syntology":null},{"url":"/paper/refocusing-is-key-to-transfer-learning","slug":"refocusing-is-key-to-transfer-learning","title":"TOAST: Transfer Learning via Attention Steering","date":"2023-05-24","arxiv_id":"2305.15542","repositories_listed":1,"syntology":null}],"syntology_records":46,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":18,"papers_placed":1,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/fine-grained-image-classification-on-stanford","since_archive":"/sota/fine-grained-image-classification-on-stanford#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/fine-grained-image-classification-on-fgvc","since_archive":"/sota/fine-grained-image-classification-on-fgvc#since-judged","papers_judged":2,"placed":0},{"leaderboard":"/sota/fine-grained-image-classification-on-cub-200-1","since_archive":"/sota/fine-grained-image-classification-on-cub-200-1#since-judged","papers_judged":2,"placed":1},{"leaderboard":"/sota/fine-grained-image-classification-on-oxford","since_archive":"/sota/fine-grained-image-classification-on-oxford#since-judged","papers_judged":11,"placed":0},{"leaderboard":"/sota/fine-grained-image-classification-on-oxford-2","since_archive":"/sota/fine-grained-image-classification-on-oxford-2#since-judged","papers_judged":2,"placed":0},{"leaderboard":"/sota/fine-grained-image-classification-on-caltech","since_archive":"/sota/fine-grained-image-classification-on-caltech#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/fine-grained-image-classification-on-food-101","since_archive":"/sota/fine-grained-image-classification-on-food-101#since-judged","papers_judged":8,"placed":0},{"leaderboard":"/sota/fine-grained-image-classification-on-sun397","since_archive":"/sota/fine-grained-image-classification-on-sun397#since-judged","papers_judged":3,"placed":0},{"leaderboard":"/sota/fine-grained-image-classification-on-mnist","since_archive":"/sota/fine-grained-image-classification-on-mnist#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":54,"papers_where_code_ran_first_page":"/task/fine-grained-image-classification/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":4,"url":"/task/fine-grained-image-classification/papers/2","json":"/task/fine-grained-image-classification/papers/2.json","rows":100},{"order":"archive","page":3,"of":4,"url":"/task/fine-grained-image-classification/papers/3","json":"/task/fine-grained-image-classification/papers/3.json","rows":100},{"order":"archive","page":4,"of":4,"url":"/task/fine-grained-image-classification/papers/4","json":"/task/fine-grained-image-classification/papers/4.json","rows":53},{"order":"ran","page":1,"of":1,"url":"/task/fine-grained-image-classification/papers/ran/1","json":"/task/fine-grained-image-classification/papers/ran/1.json","rows":54}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"35c3865378139f44473ceeee8fbc933b11116b55999359fd12006761db83ff7f","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}