{"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":"/sota/fine-grained-image-classification-on-stanford","task":{"name":"Fine-Grained Image Classification","url":"/task/fine-grained-image-classification","note":null},"dataset":{"name":"Stanford Cars","url":"/dataset/stanford-cars"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**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>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Accuracy","FLOPS","PARAMS"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction; the tokens 'score' and 'time' are not used on this page); null = not inferred, chart draws points only","by_metric":{"Accuracy":"higher","FLOPS":"lower","PARAMS":"lower"}},"counts":{"rows":83,"rows_with_code":67,"rows_with_paper_page":83,"rows_dated":83,"rows_using_additional_data":10},"rows":[{"rank_in_archive_order":1,"model":"TResnet-L + PMD","metrics":{"Accuracy":"97.3%"},"uses_additional_data":false,"paper_date":"2024-01-25","paper":"/paper/progressive-multi-task-anti-noise-learning","paper_url":"https://arxiv.org/abs/2401.14336v1","paper_title":"Progressive Multi-task Anti-Noise Learning and Distilling Frameworks for Fine-grained Vehicle Recognition","code":"https://github.com/dichao-liu/anti-noise_fgvr","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":2,"model":"CMAL-Net","metrics":{"Accuracy":"97.1%"},"uses_additional_data":true,"paper_date":"2023-03-22","paper":"/paper/learn-from-each-other-to-classify-better","paper_url":"https://www.sciencedirect.com/science/article/pii/S0031320323002509","paper_title":"Learn from Each Other to Classify Better: Cross-layer Mutual Attention Learning for Fine-grained Visual Classification","code":"https://github.com/Dichao-Liu/CMAL","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":3,"model":"I2-HOFI","metrics":{"Accuracy":"96.92%"},"uses_additional_data":false,"paper_date":"2024-10-20","paper":"/paper/interweaving-insights-high-order-feature","paper_url":"https://link.springer.com/article/10.1007/s11263-024-02260-y","paper_title":"Interweaving Insights: High-Order Feature Interaction for Fine-Grained Visual Recognition","code":"https://github.com/arindam-1991/i2-hofi","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":4,"model":"TResNet-L + ML-Decoder","metrics":{"Accuracy":"96.41%"},"uses_additional_data":true,"paper_date":"2021-11-25","paper":"/paper/ml-decoder-scalable-and-versatile","paper_url":"https://arxiv.org/abs/2111.12933v2","paper_title":"ML-Decoder: Scalable and Versatile Classification Head","code":"https://github.com/alibaba-miil/ml_decoder","n_code_links":1,"official":{"repos":["alibaba-miil/ml_decoder"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":1,"sample_list":"/paper/ml-decoder-scalable-and-versatile#ran","syntology_url":"https://syntology.ai/paper/2111.12933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.12933"}}}},{"rank_in_archive_order":5,"model":"DAT","metrics":{"Accuracy":"96.2%"},"uses_additional_data":true,"paper_date":"2018-11-16","paper":"/paper/domain-adaptive-transfer-learning-with","paper_url":"http://arxiv.org/abs/1811.07056v2","paper_title":"Domain Adaptive Transfer Learning with Specialist Models","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":6,"model":"ALIGN","metrics":{"Accuracy":"96.13%"},"uses_additional_data":true,"paper_date":"2021-02-11","paper":"/paper/scaling-up-visual-and-vision-language","paper_url":"https://arxiv.org/abs/2102.05918v2","paper_title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","code":"https://github.com/facebookresearch/metaclip","n_code_links":5,"official":null,"syntology":{"n_ran":8,"n_constructed":6,"n_ran_checked":7,"n_instrument":1,"n_unverified":2,"n_samples":10,"n_pointer_only_licence":9,"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"}}}},{"rank_in_archive_order":7,"model":"SR-GNN","metrics":{"Accuracy":"96.1","FLOPS":"9.8","PARAMS":"30.9"},"uses_additional_data":false,"paper_date":"2022-09-05","paper":"/paper/sr-gnn-spatial-relation-aware-graph-neural","paper_url":"https://arxiv.org/abs/2209.02109v1","paper_title":"SR-GNN: Spatial Relation-aware Graph Neural Network for Fine-Grained Image Categorization","code":"https://github.com/ardhendubehera/sr-gnn","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":8,"model":"EffNet-L2 (SAM)","metrics":{"Accuracy":"95.96%"},"uses_additional_data":true,"paper_date":"2020-10-03","paper":"/paper/sharpness-aware-minimization-for-efficiently-1","paper_url":"https://arxiv.org/abs/2010.01412v3","paper_title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","code":"https://github.com/davda54/sam","n_code_links":18,"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"]},"syntology":{"n_ran":15,"n_constructed":6,"n_ran_checked":13,"n_instrument":2,"n_unverified":5,"n_samples":20,"n_pointer_only_licence":6,"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"}}}},{"rank_in_archive_order":9,"model":"SaSPA + CAL","metrics":{"Accuracy":"95.72"},"uses_additional_data":false,"paper_date":"2024-06-20","paper":"/paper/advancing-fine-grained-classification-by","paper_url":"https://arxiv.org/abs/2406.14551v2","paper_title":"Advancing Fine-Grained Classification by Structure and Subject Preserving Augmentation","code":"https://github.com/eyalmichaeli/saspa-aug","n_code_links":1,"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":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":10,"model":"CAP","metrics":{"Accuracy":"95.7%"},"uses_additional_data":false,"paper_date":"2021-01-17","paper":"/paper/context-aware-attentional-pooling-cap-for","paper_url":"https://arxiv.org/abs/2101.06635v1","paper_title":"Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification","code":"https://github.com/ArdhenduBehera/cap","n_code_links":1,"official":null,"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":11,"model":"AttNet & AffNet","metrics":{"Accuracy":"95.6%"},"uses_additional_data":false,"paper_date":"2020-05-11","paper":"/paper/fine-grained-visual-classification-with","paper_url":"https://arxiv.org/abs/2005.05123v1","paper_title":"Fine-Grained Visual Classification with Efficient End-to-end Localization","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":12,"model":"CSQA-Net","metrics":{"Accuracy":"95.6%"},"uses_additional_data":false,"paper_date":"2024-03-15","paper":"/paper/context-semantic-quality-awareness-network","paper_url":"https://arxiv.org/abs/2403.10298v1","paper_title":"Context-Semantic Quality Awareness Network for Fine-Grained Visual Categorization","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":13,"model":"CAL","metrics":{"Accuracy":"95.5%"},"uses_additional_data":false,"paper_date":"2021-08-19","paper":"/paper/counterfactual-attention-learning-for-fine","paper_url":"https://arxiv.org/abs/2108.08728v2","paper_title":"Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification","code":"https://github.com/raoyongming/CAL","n_code_links":1,"official":{"repos":["raoyongming/CAL"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":7,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":8,"n_constructed":7,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_samples":11,"n_pointer_only_licence":0,"sample_list":"/paper/counterfactual-attention-learning-for-fine#ran","syntology_url":"https://syntology.ai/paper/2108.08728","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.08728"}}}},{"rank_in_archive_order":14,"model":"CCFR","metrics":{"Accuracy":"95.5%"},"uses_additional_data":false,"paper_date":"2021-02-19","paper":"/paper/re-rank-coarse-classification-with-local","paper_url":"https://arxiv.org/abs/2102.09875v1","paper_title":"Re-rank Coarse Classification with Local Region Enhanced Features for Fine-Grained Image Recognition","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":15,"model":"MPSA","metrics":{"Accuracy":"95.4%"},"uses_additional_data":false,"paper_date":"2024-08-16","paper":"/paper/multi-granularity-part-sampling-attention-for","paper_url":"https://ieeexplore.ieee.org/document/10638479","paper_title":"Multi-Granularity Part Sampling Attention for Fine-Grained Visual Classification","code":"https://github.com/mobulan/MPSA","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":16,"model":"Inceptionv4","metrics":{"Accuracy":"95.35%"},"uses_additional_data":false,"paper_date":"2021-07-19","paper":"/paper/non-binary-deep-transfer-learning-for","paper_url":"https://arxiv.org/abs/2107.08585v2","paper_title":"Non-binary deep transfer learning for image classification","code":"https://github.com/XuyangSHEN/Non-binary-deep-transfer-learning-for-image-classification","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":17,"model":"API-Net","metrics":{"Accuracy":"95.3%"},"uses_additional_data":false,"paper_date":"2020-02-24","paper":"/paper/learning-attentive-pairwise-interaction-for","paper_url":"https://arxiv.org/abs/2002.10191v1","paper_title":"Learning Attentive Pairwise Interaction for Fine-Grained Classification","code":"https://github.com/PeiqinZhuang/API-Net","n_code_links":1,"official":null,"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":2,"sample_list":"/paper/learning-attentive-pairwise-interaction-for#ran","syntology_url":"https://syntology.ai/paper/2002.10191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.10191"}}}},{"rank_in_archive_order":18,"model":"DCAL","metrics":{"Accuracy":"95.3%"},"uses_additional_data":false,"paper_date":"2022-05-04","paper":"/paper/dual-cross-attention-learning-for-fine","paper_url":"https://arxiv.org/abs/2205.02151v1","paper_title":"Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":19,"model":"PART","metrics":{"Accuracy":"95.3%"},"uses_additional_data":false,"paper_date":"2022-12-28","paper":"/paper/part-guided-relational-transformers-for-fine","paper_url":"https://arxiv.org/abs/2212.13685v1","paper_title":"Part-guided Relational Transformers for Fine-grained Visual Recognition","code":"https://github.com/icvteam/part","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":20,"model":"DenseNet161+MM+FRL","metrics":{"Accuracy":"95.2%"},"uses_additional_data":false,"paper_date":"2020-11-22","paper":"/paper/towards-class-specific-unit","paper_url":"https://arxiv.org/abs/2011.10951v2","paper_title":"Learning Class Unique Features in Fine-Grained Visual Classification","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":21,"model":"PMG","metrics":{"Accuracy":"95.1%"},"uses_additional_data":false,"paper_date":"2020-03-08","paper":"/paper/fine-grained-visual-classification-via","paper_url":"https://arxiv.org/abs/2003.03836v3","paper_title":"Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches","code":"https://github.com/PRIS-CV/PMG-Progressive-Multi-Granularity-Training","n_code_links":5,"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"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_samples":6,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":22,"model":"Multi Granularity","metrics":{"Accuracy":"95.1%"},"uses_additional_data":false,"paper_date":"2020-11-18","paper":"/paper/your-labrador-is-my-dog-fine-grained-or-not","paper_url":"https://arxiv.org/abs/2011.09040v3","paper_title":"Your \"Flamingo\" is My \"Bird\": Fine-Grained, or Not","code":"https://github.com/PRIS-CV/Fine-Grained-or-Not","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":23,"model":"TBMSL-Net","metrics":{"Accuracy":"95.0%"},"uses_additional_data":false,"paper_date":"2020-03-20","paper":"/paper/three-branch-and-mutil-scale-learning-for","paper_url":"https://arxiv.org/abs/2003.09150v3","paper_title":"Multi-branch and Multi-scale Attention Learning for Fine-Grained Visual Categorization","code":"https://github.com/ZF1044404254/TBMSL-Net","n_code_links":6,"official":null,"syntology":null},{"rank_in_archive_order":24,"model":"ELoPE","metrics":{"Accuracy":"95.0%"},"uses_additional_data":false,"paper_date":"2019-11-17","paper":"/paper/elope-fine-grained-visual-classification-with","paper_url":"https://arxiv.org/abs/1911.07344v1","paper_title":"ELoPE: Fine-Grained Visual Classification with Efficient Localization, Pooling and Embedding","code":"https://github.com/rwth-i6/fgvc/tree/master/elope_torch","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":25,"model":"ViT-NeT (SwinV2-B)","metrics":{"Accuracy":"95.0%"},"uses_additional_data":false,"paper_date":"2022-07-17","paper":"/paper/vit-net-interpretable-vision-transformers","paper_url":"https://proceedings.mlr.press/v162/kim22g/kim22g.pdf","paper_title":"ViT-NeT: Interpretable Vision Transformers with Neural Tree Decoder","code":"https://github.com/jumpsnack/ViT-NeT","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":26,"model":"AFTrans","metrics":{"Accuracy":"95.0%"},"uses_additional_data":false,"paper_date":"2021-10-04","paper":"/paper/a-free-lunch-from-vit-adaptive-attention","paper_url":"https://arxiv.org/abs/2110.01240v2","paper_title":"A free lunch from ViT:Adaptive Attention Multi-scale Fusion Transformer for Fine-grained Visual Recognition","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":27,"model":"DB","metrics":{"Accuracy":"94.9%"},"uses_additional_data":false,"paper_date":"2019-12-14","paper":"/paper/fine-grained-recognition-accounting-for","paper_url":"https://arxiv.org/abs/1912.06842v1","paper_title":"Fine-grained Recognition: Accounting for Subtle Differences between Similar Classes","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":28,"model":"Attribute Mix+","metrics":{"Accuracy":"94.9%"},"uses_additional_data":false,"paper_date":"2020-04-06","paper":"/paper/attribute-mix-semantic-data-augmentation-for","paper_url":"https://arxiv.org/abs/2004.02684v2","paper_title":"Attribute Mix: Semantic Data Augmentation for Fine Grained Recognition","code":"https://github.com/Westlake-AI/openmixup","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":29,"model":"AutoAugment","metrics":{"Accuracy":"94.8%"},"uses_additional_data":false,"paper_date":"2018-05-24","paper":"/paper/autoaugment-learning-augmentation-policies","paper_url":"http://arxiv.org/abs/1805.09501v3","paper_title":"AutoAugment: Learning Augmentation Policies from Data","code":"https://github.com/tensorflow/models/tree/master/research/autoaugment","n_code_links":33,"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"]},"syntology":{"n_ran":25,"n_constructed":0,"n_ran_checked":22,"n_instrument":3,"n_unverified":18,"n_samples":43,"n_pointer_only_licence":4,"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"}}}},{"rank_in_archive_order":30,"model":"BCN","metrics":{"Accuracy":"94.8%"},"uses_additional_data":false,"paper_date":"2019-10-28","paper":"/paper/fine-grained-visual-classification-with-batch","paper_url":"https://arxiv.org/abs/1910.12423","paper_title":"Fine-Grained Visual Classification with Batch Confusion Norm","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":31,"model":"DF-GMM","metrics":{"Accuracy":"94.8%"},"uses_additional_data":false,"paper_date":"2020-06-01","paper":"/paper/weakly-supervised-fine-grained-image-1","paper_url":"http://openaccess.thecvf.com/content_CVPR_2020/html/Wang_Weakly_Supervised_Fine-Grained_Image_Classification_via_Guassian_Mixture_Model_Oriented_CVPR_2020_paper.html","paper_title":"Weakly Supervised Fine-Grained Image Classification via Guassian Mixture Model Oriented Discriminative Learning","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":32,"model":"TransFG","metrics":{"Accuracy":"94.8%"},"uses_additional_data":false,"paper_date":"2021-03-14","paper":"/paper/transfg-a-transformer-architecture-for-fine","paper_url":"https://arxiv.org/abs/2103.07976v5","paper_title":"TransFG: A Transformer Architecture for Fine-grained Recognition","code":"https://github.com/TACJu/TransFG","n_code_links":2,"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"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":2,"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"}}}},{"rank_in_archive_order":33,"model":"CRA-CNN","metrics":{"Accuracy":"94.8%"},"uses_additional_data":false,"paper_date":"2020-09-08","paper":"/paper/contrastively-reinforced-attention","paper_url":"https://www.bmvc2020-conference.com/conference/papers/paper_0656.html","paper_title":"Contrastively-reinforced Attention Convolutional Neural Network for Fine-grained Image Recognition","code":"https://github.com/Dichao-Liu/CRA-CNN","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":34,"model":"S3N","metrics":{"Accuracy":"94.7%"},"uses_additional_data":false,"paper_date":"2019-10-01","paper":"/paper/selective-sparse-sampling-for-fine-grained","paper_url":"http://openaccess.thecvf.com/content_ICCV_2019/html/Ding_Selective_Sparse_Sampling_for_Fine-Grained_Image_Recognition_ICCV_2019_paper.html","paper_title":"Selective Sparse Sampling for Fine-Grained Image Recognition","code":"https://github.com/Yao-DD/S3N","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":35,"model":"EfficientNet-B7","metrics":{"Accuracy":"94.7%"},"uses_additional_data":false,"paper_date":"2019-05-28","paper":"/paper/efficientnet-rethinking-model-scaling-for","paper_url":"https://arxiv.org/abs/1905.11946v5","paper_title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","code":"https://github.com/ultralytics/yolov5","n_code_links":144,"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"]},"syntology":{"n_ran":198,"n_constructed":73,"n_ran_checked":157,"n_instrument":41,"n_unverified":104,"n_samples":302,"n_pointer_only_licence":113,"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"}}}},{"rank_in_archive_order":36,"model":"Grafit (RegNet-8GF)","metrics":{"Accuracy":"94.7%"},"uses_additional_data":false,"paper_date":"2020-11-25","paper":"/paper/grafit-learning-fine-grained-image","paper_url":"https://arxiv.org/abs/2011.12982v1","paper_title":"Grafit: Learning fine-grained image representations with coarse labels","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":37,"model":"GPipe","metrics":{"Accuracy":"94.6%"},"uses_additional_data":false,"paper_date":"2018-11-16","paper":"/paper/gpipe-efficient-training-of-giant-neural","paper_url":"https://arxiv.org/abs/1811.06965v5","paper_title":"GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism","code":"https://github.com/tensorflow/lingvo","n_code_links":13,"official":null,"syntology":{"n_ran":20,"n_constructed":0,"n_ran_checked":19,"n_instrument":1,"n_unverified":5,"n_samples":25,"n_pointer_only_licence":16,"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"}}}},{"rank_in_archive_order":38,"model":"Cross-X","metrics":{"Accuracy":"94.6%"},"uses_additional_data":false,"paper_date":"2019-09-10","paper":"/paper/cross-x-learning-for-fine-grained-visual","paper_url":"https://arxiv.org/abs/1909.04412v1","paper_title":"Cross-X Learning for Fine-Grained Visual Categorization","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":39,"model":"ACNet","metrics":{"Accuracy":"94.6%"},"uses_additional_data":false,"paper_date":"2019-09-25","paper":"/paper/attention-convolutional-binary-neural-tree","paper_url":"https://arxiv.org/abs/1909.11378v2","paper_title":"Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization","code":"https://github.com/FlyingMoon-GitHub/ACNet","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":40,"model":"SEB+EfficientNet-B5","metrics":{"Accuracy":"94.6%"},"uses_additional_data":false,"paper_date":"2022-05-26","paper":"/paper/on-the-eigenvalues-of-global-covariance","paper_url":"https://arxiv.org/abs/2205.13282v1","paper_title":"On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition","code":"https://github.com/KingJamesSong/DifferentiableSVD","n_code_links":1,"official":{"repos":["KingJamesSong/DifferentiableSVD"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":5,"ran_from_kinds":["official"]},"syntology":{"n_ran":12,"n_constructed":0,"n_ran_checked":9,"n_instrument":3,"n_unverified":5,"n_samples":17,"n_pointer_only_licence":1,"sample_list":"/paper/on-the-eigenvalues-of-global-covariance#ran","syntology_url":"https://syntology.ai/paper/2205.13282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.13282"}}}},{"rank_in_archive_order":41,"model":"PCA","metrics":{"Accuracy":"94.6%"},"uses_additional_data":false,"paper_date":"2021-01-21","paper":"/paper/progressive-co-attention-network-for-fine","paper_url":"https://arxiv.org/abs/2101.08527v2","paper_title":"Progressive Co-Attention Network for Fine-grained Visual Classification","code":"https://github.com/PRIS-CV/PCA-Net","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":42,"model":"WS-DAN","metrics":{"Accuracy":"94.5%"},"uses_additional_data":false,"paper_date":"2019-01-26","paper":"/paper/see-better-before-looking-closer-weakly","paper_url":"http://arxiv.org/abs/1901.09891v2","paper_title":"See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification","code":"https://github.com/wvinzh/WS_DAN_PyTorch","n_code_links":4,"official":null,"syntology":null},{"rank_in_archive_order":43,"model":"CIN","metrics":{"Accuracy":"94.5%"},"uses_additional_data":false,"paper_date":"2020-03-11","paper":"/paper/channel-interaction-networks-for-fine-grained-1","paper_url":"https://arxiv.org/abs/2003.05235v1","paper_title":"Channel Interaction Networks for Fine-Grained Image Categorization","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":44,"model":"LIO/ResNet-50 (multi-stage)","metrics":{"Accuracy":"94.5%"},"uses_additional_data":false,"paper_date":"2020-03-31","paper":"/paper/look-into-object-self-supervised-structure","paper_url":"https://arxiv.org/abs/2003.14142v1","paper_title":"Look-into-Object: Self-supervised Structure Modeling for Object Recognition","code":"https://github.com/JDAI-CV/DCL","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":45,"model":"Grad-CAM","metrics":{"Accuracy":"94.41%"},"uses_additional_data":false,"paper_date":"2021-01-24","paper":"/paper/grad-cam-guided-channel-spatial-attention","paper_url":"https://arxiv.org/abs/2101.09666v1","paper_title":"Grad-CAM guided channel-spatial attention module for fine-grained visual classification","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":46,"model":"FixSENet-154","metrics":{"Accuracy":"94.4%"},"uses_additional_data":false,"paper_date":"2019-06-14","paper":"/paper/fixing-the-train-test-resolution-discrepancy","paper_url":"https://arxiv.org/abs/1906.06423v4","paper_title":"Fixing the train-test resolution discrepancy","code":"https://github.com/facebookresearch/FixRes","n_code_links":3,"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":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":2,"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"}}}},{"rank_in_archive_order":47,"model":"Assemble-ResNet-FGVC-50","metrics":{"Accuracy":"94.4%"},"uses_additional_data":false,"paper_date":"2020-01-17","paper":"/paper/compounding-the-performance-improvements-of","paper_url":"https://arxiv.org/abs/2001.06268v2","paper_title":"Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network","code":"https://github.com/clovaai/assembled-cnn","n_code_links":1,"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"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":8,"n_samples":11,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":48,"model":"MC Loss (B-CNN)","metrics":{"Accuracy":"94.4%"},"uses_additional_data":false,"paper_date":"2020-02-11","paper":"/paper/the-devil-is-in-the-channels-mutual-channel","paper_url":"https://arxiv.org/abs/2002.04264v3","paper_title":"The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification","code":"https://github.com/frgfm/Holocron","n_code_links":3,"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"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":2,"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"}}}},{"rank_in_archive_order":49,"model":"ELP","metrics":{"Accuracy":"94.2"},"uses_additional_data":false,"paper_date":"2022-01-01","paper":"/paper/a-simple-episodic-linear-probe-improves","paper_url":"http://openaccess.thecvf.com//content/CVPR2022/html/Liang_A_Simple_Episodic_Linear_Probe_Improves_Visual_Recognition_in_the_CVPR_2022_paper.html","paper_title":"A Simple Episodic Linear Probe Improves Visual Recognition in the Wild","code":"https://github.com/JDAI-CV/DCL","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":50,"model":"MHEM (strong ResNet50 baseline)","metrics":{"Accuracy":"94.2%"},"uses_additional_data":false,"paper_date":"2022-11-21","paper":"/paper/penalizing-the-hard-example-but-not-too-much","paper_url":"https://ieeexplore.ieee.org/abstract/document/9956020","paper_title":"Penalizing the Hard Example But Not Too Much: A Strong Baseline for Fine-Grained Visual Classification","code":"https://github.com/akira-l/mhem","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":51,"model":"RDNet-S (224 res, IN-1K pretrained)","metrics":{"Accuracy":"94.2%","FLOPS":"8.7G","PARAMS":"50M"},"uses_additional_data":false,"paper_date":"2024-03-28","paper":"/paper/densenets-reloaded-paradigm-shift-beyond","paper_url":"https://arxiv.org/abs/2403.19588v2","paper_title":"DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs","code":"https://github.com/huggingface/pytorch-image-models","n_code_links":3,"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"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":52,"model":"RDNet-L (224 res, IN-1K pretrained)","metrics":{"Accuracy":"94.2%","FLOPS":"34.7G","PARAMS":"186M"},"uses_additional_data":false,"paper_date":"2024-03-28","paper":"/paper/densenets-reloaded-paradigm-shift-beyond","paper_url":"https://arxiv.org/abs/2403.19588v2","paper_title":"DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs","code":"https://github.com/huggingface/pytorch-image-models","n_code_links":3,"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"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":53,"model":"RDNet-B (224 res, IN-1K pretrained)","metrics":{"Accuracy":"94.1%","FLOPS":"15.4G","PARAMS":"87M"},"uses_additional_data":false,"paper_date":"2024-03-28","paper":"/paper/densenets-reloaded-paradigm-shift-beyond","paper_url":"https://arxiv.org/abs/2403.19588v2","paper_title":"DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs","code":"https://github.com/huggingface/pytorch-image-models","n_code_links":3,"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"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":54,"model":"GCL","metrics":{"Accuracy":"94.0%"},"uses_additional_data":false,"paper_date":"2020-02-14","paper":"/paper/graph-propagation-based-correlation-learning","paper_url":"https://www.aaai.org/Papers/AAAI/2020GB/AAAI-WangZ.4646.pdf","paper_title":"Graph-propagation based Correlation Learning for Weakly Supervised Fine-grained Image Classification","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":55,"model":"SEF","metrics":{"Accuracy":"94.0%"},"uses_additional_data":false,"paper_date":"2020-06-24","paper":"/paper/learning-semantically-enhanced-feature-for","paper_url":"https://arxiv.org/abs/2006.13457v3","paper_title":"Learning Semantically Enhanced Feature for Fine-Grained Image Classification","code":"https://github.com/cswluo/SEF","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":56,"model":"AENet","metrics":{"Accuracy":"94.0%"},"uses_additional_data":false,"paper_date":"2021-03-01","paper":"/paper/alignment-enhancement-network-for-fine","paper_url":"https://dl.acm.org/doi/abs/10.1145/3446208","paper_title":"Alignment Enhancement Network for Fine-grained Visual Categorization","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":57,"model":"NTS-Net (K=4)","metrics":{"Accuracy":"93.9%"},"uses_additional_data":false,"paper_date":"2018-09-02","paper":"/paper/learning-to-navigate-for-fine-grained","paper_url":"http://arxiv.org/abs/1809.00287v1","paper_title":"Learning to Navigate for Fine-grained Classification","code":"https://github.com/osmr/imgclsmob","n_code_links":12,"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"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":0,"n_samples":9,"n_pointer_only_licence":3,"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"}}}},{"rank_in_archive_order":58,"model":"Bamboo (ViT-B/16)","metrics":{"Accuracy":"93.9%"},"uses_additional_data":true,"paper_date":"2022-03-15","paper":"/paper/bamboo-building-mega-scale-vision-dataset","paper_url":"https://arxiv.org/abs/2203.07845v2","paper_title":"Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy","code":"https://github.com/zhangyuanhan-ai/bamboo","n_code_links":2,"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"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3,"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"}}}},{"rank_in_archive_order":59,"model":"RDNet-T (224 res, IN-1K pretrained)","metrics":{"Accuracy":"93.9%","FLOPS":"5.0G","PARAMS":"24M"},"uses_additional_data":false,"paper_date":"2024-03-28","paper":"/paper/densenets-reloaded-paradigm-shift-beyond","paper_url":"https://arxiv.org/abs/2403.19588v2","paper_title":"DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs","code":"https://github.com/huggingface/pytorch-image-models","n_code_links":3,"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"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":60,"model":"DFL-CNN","metrics":{"Accuracy":"93.8%"},"uses_additional_data":false,"paper_date":"2016-11-29","paper":"/paper/learning-a-discriminative-filter-bank-within","paper_url":"http://arxiv.org/abs/1611.09932v3","paper_title":"Learning a Discriminative Filter Bank within a CNN for Fine-grained Recognition","code":"https://github.com/jobinkv/Ongoing","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":61,"model":"TASN","metrics":{"Accuracy":"93.8%"},"uses_additional_data":false,"paper_date":"2019-03-14","paper":"/paper/looking-for-the-devil-in-the-details-learning","paper_url":"https://arxiv.org/abs/1903.06150v2","paper_title":"Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognition","code":"https://github.com/researchmm/tasn","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":62,"model":"ViT-L (attn finetune)","metrics":{"Accuracy":"93.8%"},"uses_additional_data":true,"paper_date":"2022-03-18","paper":"/paper/three-things-everyone-should-know-about","paper_url":"https://arxiv.org/abs/2203.09795v1","paper_title":"Three things everyone should know about Vision Transformers","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":8,"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"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":63,"model":"AutoFormer-S | 384","metrics":{"Accuracy":"93.4%"},"uses_additional_data":false,"paper_date":"2021-07-01","paper":"/paper/autoformer-searching-transformers-for-visual","paper_url":"https://arxiv.org/abs/2107.00651v1","paper_title":"AutoFormer: Searching Transformers for Visual Recognition","code":"https://github.com/microsoft/AutoML","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":64,"model":"MPN-COV","metrics":{"Accuracy":"93.3%"},"uses_additional_data":false,"paper_date":"2017-12-04","paper":"/paper/towards-faster-training-of-global-covariance","paper_url":"http://arxiv.org/abs/1712.01034v2","paper_title":"Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalization","code":"https://github.com/osmr/imgclsmob","n_code_links":4,"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"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":1,"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"}}}},{"rank_in_archive_order":65,"model":"DeiT-B","metrics":{"Accuracy":"93.3%","PARAMS":"86M"},"uses_additional_data":false,"paper_date":"2020-12-23","paper":"/paper/training-data-efficient-image-transformers","paper_url":"https://arxiv.org/abs/2012.12877v2","paper_title":"Training data-efficient image transformers & distillation through attention","code":"https://github.com/huggingface/transformers","n_code_links":40,"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"]},"syntology":{"n_ran":12,"n_constructed":1,"n_ran_checked":9,"n_instrument":3,"n_unverified":7,"n_samples":19,"n_pointer_only_licence":3,"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"}}}},{"rank_in_archive_order":66,"model":"ResNet101-swp","metrics":{"Accuracy":"93.1%"},"uses_additional_data":false,"paper_date":"2017-04-04","paper":"/paper/deep-cnns-with-spatially-weighted-pooling-for","paper_url":"https://ieeexplore.ieee.org/document/7891907","paper_title":"Deep CNNs With Spatially Weighted Pooling for Fine-Grained Car Recognition","code":"https://github.com/duongttr/SWP","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":67,"model":"MAMC","metrics":{"Accuracy":"93.0%"},"uses_additional_data":false,"paper_date":"2018-06-14","paper":"/paper/multi-attention-multi-class-constraint-for","paper_url":"http://arxiv.org/abs/1806.05372v1","paper_title":"Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition","code":"https://github.com/xcnkx/fine_grained_classification","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":68,"model":"NAT-M4","metrics":{"Accuracy":"92.9%","FLOPS":"369M","PARAMS":"3.7M"},"uses_additional_data":false,"paper_date":"2020-05-12","paper":"/paper/neural-architecture-transfer","paper_url":"https://arxiv.org/abs/2005.05859v2","paper_title":"Neural Architecture Transfer","code":"https://github.com/human-analysis/neural-architecture-transfer","n_code_links":2,"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":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1,"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"}}}},{"rank_in_archive_order":69,"model":"PC-DenseNet-161","metrics":{"Accuracy":"92.86%"},"uses_additional_data":false,"paper_date":"2017-05-22","paper":"/paper/pairwise-confusion-for-fine-grained-visual","paper_url":"http://arxiv.org/abs/1705.08016v3","paper_title":"Pairwise Confusion for Fine-Grained Visual Classification","code":"https://github.com/abhimanyudubey/confusion","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":70,"model":"MACNN","metrics":{"Accuracy":"92.8"},"uses_additional_data":false,"paper_date":"2017-10-01","paper":"/paper/learning-multi-attention-convolutional-neural","paper_url":"http://openaccess.thecvf.com/content_iccv_2017/html/Zheng_Learning_Multi-Attention_Convolutional_ICCV_2017_paper.html","paper_title":"Learning Multi-Attention Convolutional Neural Network for Fine-Grained Image Recognition","code":"https://github.com/minfengUCAS/Muti-Attention-CNN","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":71,"model":"ResNet50 (A1)","metrics":{"Accuracy":"92.7%","FLOPS":"4.1B","PARAMS":"24M"},"uses_additional_data":false,"paper_date":"2021-10-01","paper":"/paper/resnet-strikes-back-an-improved-training","paper_url":"https://arxiv.org/abs/2110.00476v1","paper_title":"ResNet strikes back: An improved training procedure in timm","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":14,"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":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":72,"model":"NAT-M3","metrics":{"Accuracy":"92.6%","FLOPS":"289M","PARAMS":"3.5M"},"uses_additional_data":false,"paper_date":"2020-05-12","paper":"/paper/neural-architecture-transfer","paper_url":"https://arxiv.org/abs/2005.05859v2","paper_title":"Neural Architecture Transfer","code":"https://github.com/human-analysis/neural-architecture-transfer","n_code_links":2,"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":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1,"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"}}}},{"rank_in_archive_order":73,"model":"CS-Parts","metrics":{"Accuracy":"92.5%"},"uses_additional_data":false,"paper_date":"2019-09-16","paper":"/paper/classification-specific-parts-for-improving","paper_url":"https://arxiv.org/abs/1909.07075v1","paper_title":"Classification-Specific Parts for Improving Fine-Grained Visual Categorization","code":"https://github.com/DiKorsch/l1_parts","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":74,"model":"CS-Part","metrics":{"Accuracy":"92.5%"},"uses_additional_data":false,"paper_date":"2019-09-16","paper":"/paper/classification-specific-parts-for-improving","paper_url":"https://arxiv.org/abs/1909.07075v1","paper_title":"Classification-Specific Parts for Improving Fine-Grained Visual Categorization","code":"https://github.com/DiKorsch/l1_parts","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":75,"model":"NAT-M2","metrics":{"Accuracy":"92.2%","FLOPS":"222M","PARAMS":"2.7M"},"uses_additional_data":false,"paper_date":"2020-05-12","paper":"/paper/neural-architecture-transfer","paper_url":"https://arxiv.org/abs/2005.05859v2","paper_title":"Neural Architecture Transfer","code":"https://github.com/human-analysis/neural-architecture-transfer","n_code_links":2,"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":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1,"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"}}}},{"rank_in_archive_order":76,"model":"ResNet-50","metrics":{"Accuracy":"91.06%"},"uses_additional_data":false,"paper_date":"2023-08-25","paper":"/paper/advisingnets-learning-to-distinguish-correct","paper_url":"https://arxiv.org/abs/2308.13651v5","paper_title":"PCNN: Probable-Class Nearest-Neighbor Explanations Improve Fine-Grained Image Classification Accuracy for AIs and Humans","code":"https://github.com/giangnguyen2412/PCNN-src-code-TMRL2024","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":77,"model":"NAT-M1","metrics":{"Accuracy":"90.9%","FLOPS":"165M","PARAMS":"2.4M"},"uses_additional_data":false,"paper_date":"2020-05-12","paper":"/paper/neural-architecture-transfer","paper_url":"https://arxiv.org/abs/2005.05859v2","paper_title":"Neural Architecture Transfer","code":"https://github.com/human-analysis/neural-architecture-transfer","n_code_links":2,"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":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1,"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"}}}},{"rank_in_archive_order":78,"model":"BYOL+CVSA (ResNet-50)","metrics":{"Accuracy":"89.76%"},"uses_additional_data":false,"paper_date":"2021-06-30","paper":"/paper/align-yourself-self-supervised-pre-training","paper_url":"https://arxiv.org/abs/2106.15788v4","paper_title":"Exploring Localization for Self-supervised Fine-grained Contrastive Learning","code":"https://github.com/Westlake-AI/openmixup","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":79,"model":"ResMLP-24","metrics":{"Accuracy":"89.5%"},"uses_additional_data":false,"paper_date":"2021-05-07","paper":"/paper/resmlp-feedforward-networks-for-image","paper_url":"https://arxiv.org/abs/2105.03404v2","paper_title":"ResMLP: Feedforward networks for image classification with data-efficient training","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":19,"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"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_samples":7,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":80,"model":"MPFG + CLIP","metrics":{"Accuracy":"86.79"},"uses_additional_data":true,"paper_date":"2023-08-08","paper":"/paper/multiscale-patch-based-feature-graphs-for","paper_url":"https://www.sciencedirect.com/science/article/pii/S0957417423016184","paper_title":"Multiscale patch-based feature graphs for image classification","code":"https://github.com/mvtodescato/MultiscaleGraphFeatures","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":81,"model":"ResMLP-12","metrics":{"Accuracy":"84.6%"},"uses_additional_data":false,"paper_date":"2021-05-07","paper":"/paper/resmlp-feedforward-networks-for-image","paper_url":"https://arxiv.org/abs/2105.03404v2","paper_title":"ResMLP: Feedforward networks for image classification with data-efficient training","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":19,"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"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_samples":7,"n_pointer_only_licence":0,"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"}}}},{"rank_in_archive_order":82,"model":"SEER (RegNet10B)","metrics":{"Accuracy":"68.03%"},"uses_additional_data":true,"paper_date":"2022-02-16","paper":"/paper/vision-models-are-more-robust-and-fair-when","paper_url":"https://arxiv.org/abs/2202.08360v2","paper_title":"Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision","code":"https://github.com/facebookresearch/vissl","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":83,"model":"MANO-tiny","metrics":{"Accuracy":"65.68"},"uses_additional_data":true,"paper_date":"2025-07-03","paper":"/paper/linear-attention-with-global-context-a-1","paper_url":"https://arxiv.org/abs/2507.02748v1","paper_title":"Linear Attention with Global Context: A Multipole Attention Mechanism for Vision and Physics","code":"https://github.com/AlexColagrande/MANO","n_code_links":1,"official":null,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"adjudicator":"Claude Opus 5.5","adjudicator_from":"groundwork/59_code_with_papers/LB_EXTRACTOR_PREREG.md (not recorded in lb_measurement.json; the file's frozen_commit, measured_on and counts equal the run the pre-registration records)","adjudicator_sensitivity":[69,70],"adjudicator_specificity":[101,103],"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication by a model (adjudicator) of accepted entries on a held-out split of archive papers, rules frozen before the test; adjudicator_sensitivity and adjudicator_specificity are its own controls as [judged right, of]; it was not measured on the newer papers placed here","measurement_sentence":"Measured before publishing, on held-out archive papers: the extractor was given 883 of them and produced output for 881 (the other 2 had no title and were excluded before any model call, so they are not part of this measurement). A model adjudicator (Claude Opus 5.5), blind to which entries were real, judged 108 of 110 accepted entries correct on those held-out archive papers; its own controls: 69 of 70 archive-confirmed entries judged true, 101 of 103 corrupted copies judged false. It was not measured on the newer papers whose results are placed on this site.","coverage":{"sentence":"Syntology has checked 8,886 of the 18,637 papers on this site that are newer than the archive (for 3,717 of them no archive leaderboard matched the paper's tables, so there was nothing further to check); 733 were read and have nothing to place (arXiv has no HTML version of the paper, or that version has no tables), 41 could not be read (the extractor's reply could not be parsed), and results from the other 8,977 appear after they are checked.","complete":false,"papers_newer_than_archive":18637,"papers_checked":8886,"papers_checked_no_leaderboard_matched":3717,"papers_read_nothing_to_place":733,"papers_could_not_be_read":41,"papers_could_not_be_read_by_status":{"unparseable":41},"papers_extracted_not_yet_verified":0,"boards_without_verdict":3,"papers_not_yet_extracted":8975},"board_status":{"sentence":"Of the 8,888 newer papers whose tables Syntology has read (8,886 checked in full and 2 with a leaderboard still awaiting a verdict), 9 had this board among the leaderboards the extractor considered for their tables (it keeps at most 10 boards per paper and 4 per dataset; the lists of 1,587 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and 1 proposed a result, which gave no cell that passed the extractor's own checks; none await a verdict and none were placed.","note":"papers, from the extractor's own records, over the newer papers whose tables were read; proposed = no_cell_passed_checks + rejected_by_independent_check + accepted_not_placed + awaiting_verdict + placed; counts, never a rate","eligible":true,"eligible_note":"false when the extractor never considers this board: it loads only boards with archive rows and at least one metric column (lb_extract.py Boards), so no newer paper can be proposed here; archive_rows and metric_columns say which","archive_rows":83,"metric_columns":3,"papers_read":8888,"papers_read_checked":8886,"papers_read_awaiting_verdict":2,"papers_read_verified":8888,"papers_read_not_yet_verified":0,"papers_read_at_candidate_cap":1596,"papers_read_list_full_without_this_board":1587,"candidates":9,"candidates_capped_note":"candidates = papers that had this board among the leaderboards the extractor considered for their tables; the extractor keeps at most 10 per paper and 4 per dataset, so a board crowded out of a paper's list is not counted and candidates is a floor; papers_read_list_full_without_this_board counts the read papers whose list did not hold this board and had reached 10, or held 4 boards of this board's dataset (the only papers that could have crowded it out); papers_read_at_candidate_cap counts, over every board, the papers whose list reached 10","proposed":1,"no_cell_passed_checks":1,"rejected_by_independent_check":0,"accepted_not_placed":0,"awaiting_verdict":0,"placed":0,"placed_entries_listed":0,"file_lines_unreadable_as_read":0,"since_line":"Since the archive (Syntology): none placed; 1 newer paper judged to report on this board so far"},"judged_to_report":{"heading":"Newer papers whose tables Claude Sonnet 4.5 judged to report on this benchmark (a model's judgement, not a result; newest first by arXiv id)","judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"a_record_without_a_model":false,"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","order":"newest first by arXiv id (the identifier's order, not a rank)","outcomes":{"placed":"placed","no_cell_passed_checks":"no cell passed the extractor's checks","refused_by_rule":"refused by a rule","rejected":"rejected by the independent check","accepted_not_placed":"accepted by the independent check but not placed by this site","awaiting":"awaiting a verdict"},"reason_note":"for refused_by_rule, the rules' plain words for the reason codes the record gives (never the quoted or the actual cell text); null for every other outcome","total":1,"shown_on_page":1,"no_cell_split":{"no_cell_passed_checks_in_ledger":1,"rows_refused_by_rule":1,"rows_no_cell_passed_checks":0},"rows":[{"arxiv_id":"2603.07523","outcome":"refused_by_rule","reason":"the row label the model quoted is not the row's label; the table's column header does not name the leaderboard's metric"}]},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per row: of M harvested code samples from that row's paper, n_ran executed on a synthesized fixture (n_ran = n_ran_checked + n_instrument; n_instrument counts failures of Syntology's instrument, not of the code); the other M - n_ran are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","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)"},"rows_with_graph_line":32,"rows_with_any_sample_ran":24,"rows_with_a_run_with_no_instrument_failure":23,"official":{"state_rule":"the archive's official repositories have samples for this paper that ran: 'official (archive's flag): N ran' (N counts them, instrument failures included); they have samples, none ran: 'official: harvested, nothing ran'; they have no sample for this paper and another sample ran: 'community repositories only' when every sample that ran came from a repository the archive lists for the paper but neither marks official nor records as mentioned in it, or one Syntology harvested outside the archive's links, else 'official: no sample here; runs from other or unrecorded repositories' (a repository named in the paper or found in its text by Syntology, or no repository recorded); otherwise 'official: harvested for another paper' or 'official: not harvested'. Absent when the archive marks no repository official. Official is the archive's is_official flag, not an authorship verdict","flag":"the archive's is_official flag for the paper's code link; not a verdict on who wrote the code","rows_with_an_archive_official_repository":28,"rows_whose_official_repository_has_a_sample_that_ran":15,"rows_whose_official_repository_has_a_run_with_no_instrument_failure":14,"rows_community_repositories_only":5,"rows_runs_from_other_or_unrecorded_repositories":1,"note":"rows[].official, per row with a graph line: repos (marked official in the archive), state, n_ran and n_unverified (samples from those repositories), and ran_from_kinds (the kinds of repository the paper's samples that ran came from; 'unlocated' is no repository recorded)"},"filters":{"ran_modes":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"the page's filters hide rows and never renumber them; they read the Ran cell's counts, the same figures rows[].syntology and rows[].official carry"},"row_route":"rows[].syntology 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","distinct_papers_with_graph_line":25,"distinct_papers_with_any_sample_ran":20,"distinct_papers_with_a_run_with_no_instrument_failure":19,"samples_over_distinct_papers":{"n_ran":340,"n_constructed":93,"n_ran_checked":272,"n_instrument":68,"n_unverified":174,"n_samples":514,"n_pointer_only_licence":169,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":354,"n_constructed":93,"n_ran_checked":286,"n_instrument":68,"n_unverified":179,"n_samples":533,"n_pointer_only_licence":172,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}},"record_sha256":"624e3357b9658a7d83466e8d0a39423d1728952a747bd80976ed0b00b0a858ff","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}