{"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-recognition","name":"Fine-Grained Image Recognition","slug":"fine-grained-image-recognition","description_markdown":null,"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":72,"papers_with_code":39,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"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":12,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/fine-grained-image-recognition-on-oven","slug":"fine-grained-image-recognition-on-oven","dataset":"OVEN","dataset_url":"/dataset/oven","rows_in_archive":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PaLI-X","paper_title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","paper_url":"/paper/pali-x-on-scaling-up-a-multilingual-vision","paper_date":"2023-05-29","arxiv_id":"2305.18565","code_links":[{"title":"kyegomez/PALI","url":"https://github.com/kyegomez/PALI"},{"title":"doc-doc/NExT-OE","url":"https://github.com/doc-doc/NExT-OE"}],"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":4,"n_no_contract":1,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 4 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pali-x-on-scaling-up-a-multilingual-vision#ran","syntology_url":"https://syntology.ai/paper/2305.18565","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18565"}},"official":null}}},{"leaderboard":"/sota/fine-grained-image-recognition-on-cnfood-241","slug":"fine-grained-image-recognition-on-cnfood-241","dataset":"CNFOOD-241-Chen","dataset_url":"/dataset/cnfood-241-chen","rows_in_archive":2,"metrics":["Top-1 accuracy"],"first_row_in_archive_order":{"model":"Res-VMamba-S","paper_title":"Res-VMamba: Fine-Grained Food Category Visual Classification Using Selective State Space Models with Deep Residual Learning","paper_url":"/paper/res-vmamba-fine-grained-food-category-visual","paper_date":"2024-02-24","arxiv_id":"2402.15761","code_links":[{"title":"chishengchen/resvmamba","url":"https://github.com/chishengchen/resvmamba"}],"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":3,"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/res-vmamba-fine-grained-food-category-visual#ran","syntology_url":"https://syntology.ai/paper/2402.15761","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15761"}},"official":{"repos":["chishengchen/resvmamba"],"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"]}}}},{"leaderboard":"/sota/fine-grained-image-recognition-on-cub-200","slug":"fine-grained-image-recognition-on-cub-200","dataset":"CUB-200-2011","dataset_url":"/dataset/cub-200-2011","rows_in_archive":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PIM","paper_title":"A Novel Plug-in Module for Fine-Grained Visual Classification","paper_url":"/paper/a-novel-plug-in-module-for-fine-grained-1","paper_date":"2022-02-08","arxiv_id":"2202.03822","code_links":[{"title":"chou141253/fgvc-pim","url":"https://github.com/chou141253/fgvc-pim"}],"syntology":null}},{"leaderboard":"/sota/fine-grained-image-recognition-on-cub-birds","slug":"fine-grained-image-recognition-on-cub-birds","dataset":"CUB Birds","dataset_url":"/dataset/cub-200-2011","rows_in_archive":2,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"HOI-Net","paper_title":"High-Order-Interaction for weakly supervised Fine-Grained Visual Categorization","paper_url":"/paper/high-order-interaction-for-weakly-supervised","paper_date":"2021-11-13","arxiv_id":null,"code_links":[{"title":"puallee/HOI-Net","url":"https://github.com/puallee/HOI-Net"}],"syntology":null}}],"datasets":[{"url":"/dataset/cub-200-2011","name":"CUB-200-2011","full_name":"Caltech-UCSD Birds-200-2011","num_papers_in_archive":2235},{"url":"/dataset/omnibenchmark","name":"OmniBenchmark","full_name":"","num_papers_in_archive":29},{"url":"/dataset/oven","name":"OVEN","full_name":"Open-domain Visual Entity Recognition","num_papers_in_archive":19},{"url":"/dataset/webfg-496","name":"WebFG-496","full_name":"","num_papers_in_archive":7},{"url":"/dataset/cub-gha","name":"CUB-GHA","full_name":"CUB Gaze-based Human Attention","num_papers_in_archive":4},{"url":"/dataset/goldfinch","name":"Goldfinch","full_name":"GOogLe image-search Dataset","num_papers_in_archive":3},{"url":"/dataset/daplankton","name":"DAPlankton","full_name":"","num_papers_in_archive":2},{"url":"/dataset/ultra-fine-grained-leaves-cotton-soyageing","name":"Ultra Fine-Grained Leaves (Cotton, SoyAgeing, SoyGene, SoyGlobal, SoyLocal)","full_name":"","num_papers_in_archive":2},{"url":"/dataset/cnfood-241-chen","name":"CNFOOD-241-Chen","full_name":"CNFOOD-241-Chen","num_papers_in_archive":1},{"url":"/dataset/crowd-activity-dataset","name":"Crowd Activity Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/fruit-salad","name":"fruit-SALAD","full_name":"","num_papers_in_archive":1},{"url":"/dataset/wikichurches","name":"WikiChurches","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/image-recognition","name":"Image Recognition"}],"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":1,"rows_per_page":100,"shown":72,"of":72,"of_with_code":39,"tagged_in_all":72,"counts":{"archive_papers_tagged":72,"with_a_code_link":39,"where_syntology_ran_a_sample":8,"not_listed_spam_title":0,"listed":72,"listed_where_code_ran":8,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":5,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":5,"listed_every_run_a_failure_of_syntologys_instrument":3,"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/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/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/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/hawkeye-a-pytorch-based-library-for-fine","slug":"hawkeye-a-pytorch-based-library-for-fine","title":"Hawkeye: A PyTorch-based Library for Fine-Grained Image Recognition with Deep Learning","date":"2023-10-14","arxiv_id":"2310.09600","repositories_listed":2,"syntology":null},{"url":"/paper/pali-x-on-scaling-up-a-multilingual-vision","slug":"pali-x-on-scaling-up-a-multilingual-vision","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","date":"2023-05-29","arxiv_id":"2305.18565","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":4,"n_no_contract":1,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 4 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pali-x-on-scaling-up-a-multilingual-vision#ran","syntology_url":"https://syntology.ai/paper/2305.18565","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18565"}},"official":null}},{"url":"/paper/open-domain-visual-entity-recognition-towards","slug":"open-domain-visual-entity-recognition-towards","title":"Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities","date":"2023-02-22","arxiv_id":"2302.11154","repositories_listed":2,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/open-domain-visual-entity-recognition-towards#ran","syntology_url":"https://syntology.ai/paper/2302.11154","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.11154"}},"official":{"repos":["edchengg/oven_eval"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/patch-autoaugment","slug":"patch-autoaugment","title":"Local Patch AutoAugment with Multi-Agent Collaboration","date":"2021-03-20","arxiv_id":"2103.11099","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/cross-layer-cache-aggregation-for-token","slug":"cross-layer-cache-aggregation-for-token","title":"Cross-Layer Cache Aggregation for Token Reduction in Ultra-Fine-Grained Image Recognition","date":"2024-12-31","arxiv_id":"2501.00243","repositories_listed":1,"syntology":null},{"url":"/paper/down-sampling-inter-layer-adapter-for","slug":"down-sampling-inter-layer-adapter-for","title":"Down-Sampling Inter-Layer Adapter for Parameter and Computation Efficient Ultra-Fine-Grained Image Recognition","date":"2024-09-17","arxiv_id":"2409.11051","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-fine-grained-visual-recognition-in","slug":"enhancing-fine-grained-visual-recognition-in","title":"Enhancing Fine-Grained Visual Recognition in the Low-Data Regime Through Feature Magnitude Regularization","date":"2024-09-03","arxiv_id":"2409.01672","repositories_listed":1,"syntology":null},{"url":"/paper/global-local-similarity-for-efficient-fine","slug":"global-local-similarity-for-efficient-fine","title":"Global-Local Similarity for Efficient Fine-Grained Image Recognition with Vision Transformers","date":"2024-07-17","arxiv_id":"2407.12891","repositories_listed":1,"syntology":null},{"url":"/paper/res-vmamba-fine-grained-food-category-visual","slug":"res-vmamba-fine-grained-food-category-visual","title":"Res-VMamba: Fine-Grained Food Category Visual Classification Using Selective State Space Models with Deep Residual Learning","date":"2024-02-24","arxiv_id":"2402.15761","repositories_listed":1,"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":3,"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/res-vmamba-fine-grained-food-category-visual#ran","syntology_url":"https://syntology.ai/paper/2402.15761","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15761"}},"official":{"repos":["chishengchen/resvmamba"],"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/fine-grained-recognition-with-learnable","slug":"fine-grained-recognition-with-learnable","title":"Fine-grained Recognition with Learnable Semantic Data Augmentation","date":"2023-09-01","arxiv_id":"2309.00399","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":7,"phrase":"4 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; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/fine-grained-recognition-with-learnable#ran","syntology_url":"https://syntology.ai/paper/2309.00399","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.00399"}},"official":{"repos":["LeapLabTHU/LearnableISDA"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/ppl-pairwise-prototype-learning-for-masked","slug":"ppl-pairwise-prototype-learning-for-masked","title":"PPL: Pairwise Prototype Learning for Masked Face Recognition","date":"2022-11-21","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/taxonomy-and-evolution-predicting-using-deep","slug":"taxonomy-and-evolution-predicting-using-deep","title":"Taxonomy and evolution predicting using deep learning in images","date":"2022-06-28","arxiv_id":"2206.14011","repositories_listed":1,"syntology":null},{"url":"/paper/making-heads-or-tails-towards-semantically","slug":"making-heads-or-tails-towards-semantically","title":"Making Heads or Tails: Towards Semantically Consistent Visual Counterfactuals","date":"2022-03-24","arxiv_id":"2203.12892","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"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) · 3 unverified","sample_list":"/paper/making-heads-or-tails-towards-semantically#ran","syntology_url":"https://syntology.ai/paper/2203.12892","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.12892"}},"official":{"repos":["facebookresearch/visual-counterfactuals"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/a-novel-plug-in-module-for-fine-grained-1","slug":"a-novel-plug-in-module-for-fine-grained-1","title":"A Novel Plug-in Module for Fine-Grained Visual Classification","date":"2022-02-08","arxiv_id":"2202.03822","repositories_listed":1,"syntology":null},{"url":"/paper/high-order-interaction-for-weakly-supervised","slug":"high-order-interaction-for-weakly-supervised","title":"High-Order-Interaction for weakly supervised Fine-Grained Visual Categorization","date":"2021-11-13","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/the-curious-layperson-fine-grained-image","slug":"the-curious-layperson-fine-grained-image","title":"The Curious Layperson: Fine-Grained Image Recognition without Expert Labels","date":"2021-11-05","arxiv_id":"2111.03651","repositories_listed":1,"syntology":null},{"url":"/paper/attend-and-guide-ag-net-a-keypoints-driven","slug":"attend-and-guide-ag-net-a-keypoints-driven","title":"Attend and Guide (AG-Net): A Keypoints-driven Attention-based Deep Network for Image Recognition","date":"2021-10-23","arxiv_id":"2110.12183","repositories_listed":1,"syntology":null},{"url":"/paper/fine-grained-hand-gesture-recognition-in","slug":"fine-grained-hand-gesture-recognition-in","title":"Fine-grained Hand Gesture Recognition in Multi-viewpoint Hand Hygiene","date":"2021-09-07","arxiv_id":"2109.02917","repositories_listed":1,"syntology":null},{"url":"/paper/counterfactual-attention-learning-for-fine","slug":"counterfactual-attention-learning-for-fine","title":"Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification","date":"2021-08-19","arxiv_id":"2108.08728","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":7,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","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"}},"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"]}}},{"url":"/paper/align-yourself-self-supervised-pre-training","slug":"align-yourself-self-supervised-pre-training","title":"Exploring Localization for Self-supervised Fine-grained Contrastive Learning","date":"2021-06-30","arxiv_id":"2106.15788","repositories_listed":1,"syntology":null},{"url":"/paper/danish-fungi-2020-not-just-another-image","slug":"danish-fungi-2020-not-just-another-image","title":"Danish Fungi 2020 -- Not Just Another Image Recognition Dataset","date":"2021-03-18","arxiv_id":"2103.10107","repositories_listed":1,"syntology":null},{"url":"/paper/neural-prototype-trees-for-interpretable-fine","slug":"neural-prototype-trees-for-interpretable-fine","title":"Neural Prototype Trees for Interpretable Fine-grained Image Recognition","date":"2020-12-03","arxiv_id":"2012.02046","repositories_listed":1,"syntology":null},{"url":"/paper/how-well-do-self-supervised-models-transfer","slug":"how-well-do-self-supervised-models-transfer","title":"How Well Do Self-Supervised Models Transfer?","date":"2020-11-26","arxiv_id":"2011.13377","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/how-well-do-self-supervised-models-transfer#ran","syntology_url":"https://syntology.ai/paper/2011.13377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.13377"}},"official":{"repos":["linusericsson/ssl-transfer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/contrastively-reinforced-attention","slug":"contrastively-reinforced-attention","title":"Contrastively-reinforced Attention Convolutional Neural Network for Fine-grained Image Recognition","date":"2020-09-08","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/semi-supervised-recognition-under-a-noisy-and","slug":"semi-supervised-recognition-under-a-noisy-and","title":"Semi-Supervised Recognition under a Noisy and Fine-grained Dataset","date":"2020-06-18","arxiv_id":"2006.10702","repositories_listed":1,"syntology":null},{"url":"/paper/epillid-dataset-a-low-shot-fine-grained","slug":"epillid-dataset-a-low-shot-fine-grained","title":"ePillID Dataset: A Low-Shot Fine-Grained Benchmark for Pill Identification","date":"2020-05-28","arxiv_id":"2005.14288","repositories_listed":1,"syntology":null},{"url":"/paper/learning-deep-bilinear-transformation-for","slug":"learning-deep-bilinear-transformation-for","title":"Learning Deep Bilinear Transformation for Fine-grained Image Representation","date":"2019-11-09","arxiv_id":"1911.03621","repositories_listed":1,"syntology":null},{"url":"/paper/selective-sparse-sampling-for-fine-grained","slug":"selective-sparse-sampling-for-fine-grained","title":"Selective Sparse Sampling for Fine-Grained Image Recognition","date":"2019-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/pay-attention-to-the-activations-a-modular","slug":"pay-attention-to-the-activations-a-modular","title":"Pay attention to the activations: a modular attention mechanism for fine-grained image recognition","date":"2019-07-30","arxiv_id":"1907.13075","repositories_listed":1,"syntology":null},{"url":"/paper/deep-learning-for-fine-grained-image-analysis","slug":"deep-learning-for-fine-grained-image-analysis","title":"Deep Learning for Fine-Grained Image Analysis: A Survey","date":"2019-07-06","arxiv_id":"1907.03069","repositories_listed":1,"syntology":null},{"url":"/paper/looking-for-the-devil-in-the-details-learning","slug":"looking-for-the-devil-in-the-details-learning","title":"Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognition","date":"2019-03-14","arxiv_id":"1903.06150","repositories_listed":1,"syntology":null},{"url":"/paper/fine-grained-representation-learning-and","slug":"fine-grained-representation-learning-and","title":"Fine-Grained Representation Learning and Recognition by Exploiting Hierarchical Semantic Embedding","date":"2018-08-14","arxiv_id":"1808.04505","repositories_listed":1,"syntology":null},{"url":"/paper/multi-attention-multi-class-constraint-for","slug":"multi-attention-multi-class-constraint-for","title":"Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition","date":"2018-06-14","arxiv_id":"1806.05372","repositories_listed":1,"syntology":null},{"url":"/paper/piecewise-classifier-mappings-learning-fine","slug":"piecewise-classifier-mappings-learning-fine","title":"Piecewise classifier mappings: Learning fine-grained learners for novel categories with few examples","date":"2018-05-11","arxiv_id":"1805.04288","repositories_listed":1,"syntology":null},{"url":"/paper/deepfood-deep-learning-based-food-image","slug":"deepfood-deep-learning-based-food-image","title":"DeepFood: Deep Learning-Based Food Image Recognition for Computer-Aided Dietary Assessment","date":"2016-06-17","arxiv_id":"1606.05675","repositories_listed":1,"syntology":null},{"url":"/paper/structural-feature-enhanced-transformer-for","slug":"structural-feature-enhanced-transformer-for","title":"Structural feature enhanced transformer for fine-grained image recognition","date":"2025-06-14","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"open-set-recognition-of-novel-species-in","title":"Open-Set Recognition of Novel Species in Biodiversity Monitoring","date":"2025-03-03","arxiv_id":"2503.01691","repositories_listed":0,"syntology":null},{"url":"/paper/img-diff-contrastive-data-synthesis-for","slug":"img-diff-contrastive-data-synthesis-for","title":"Img-Diff: Contrastive Data Synthesis for Multimodal Large Language Models","date":"2024-08-08","arxiv_id":"2408.04594","repositories_listed":0,"syntology":null},{"url":null,"slug":"gcam-gaussian-and-causal-attention-model-of","title":"GCAM: Gaussian and causal-attention model of food fine-grained recognition","date":"2024-03-18","arxiv_id":"2403.12109","repositories_listed":0,"syntology":null},{"url":"/paper/dining-on-details-llm-guided-expert-networks","slug":"dining-on-details-llm-guided-expert-networks","title":"Dining on Details: LLM-Guided Expert Networks for Fine-Grained Food Recognition","date":"2023-10-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"complementary-frequency-varying-awareness","title":"Complementary Frequency-Varying Awareness Network for Open-Set Fine-Grained Image Recognition","date":"2023-07-14","arxiv_id":"2307.07214","repositories_listed":0,"syntology":null},{"url":"/paper/retrieval-enhanced-contrastive-vision-text","slug":"retrieval-enhanced-contrastive-vision-text","title":"Retrieval-Enhanced Contrastive Vision-Text Models","date":"2023-06-12","arxiv_id":"2306.07196","repositories_listed":0,"syntology":null},{"url":"/paper/feature-channel-adaptive-enhancement-for-fine","slug":"feature-channel-adaptive-enhancement-for-fine","title":"Feature Channel Adaptive Enhancement for Fine-Grained Visual Classification","date":"2023-05-11","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"application-of-attention-based-siamese","title":"Application of attention-based Siamese composite neural network in medical image recognition","date":"2023-04-19","arxiv_id":"2304.09783","repositories_listed":0,"syntology":null},{"url":null,"slug":"elfis-expert-learning-for-fine-grained-image","title":"ELFIS: Expert Learning for Fine-grained Image Recognition Using Subsets","date":"2023-03-16","arxiv_id":"2303.09269","repositories_listed":0,"syntology":null},{"url":null,"slug":"siamese-transformer-with-hierarchical-concept","title":"Siamese transformer with hierarchical concept embedding for fine-grained image recognition","date":"2023-01-31","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"spatial-temporal-attention-network-for-open","title":"Spatial-Temporal Attention Network for Open-Set Fine-Grained Image Recognition","date":"2022-11-25","arxiv_id":"2211.13940","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-deep-optimal-embeddings-with","title":"Learning Deep Optimal Embeddings with Sinkhorn Divergences","date":"2022-09-14","arxiv_id":"2209.06469","repositories_listed":0,"syntology":null},{"url":null,"slug":"selectaugment-hierarchical-deterministic","title":"SelectAugment: Hierarchical Deterministic Sample Selection for Data Augmentation","date":"2021-12-06","arxiv_id":"2112.02862","repositories_listed":0,"syntology":null},{"url":null,"slug":"full-attention-based-neural-architecture","title":"Full-attention based Neural Architecture Search using Context Auto-regression","date":"2021-11-13","arxiv_id":"2111.07139","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-image-analysis-with-deep","title":"Fine-Grained Image Analysis with Deep Learning: A Survey","date":"2021-11-11","arxiv_id":"2111.06119","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-canonical-3d-object-representation","title":"Learning Canonical 3D Object Representation for Fine-Grained Recognition","date":"2021-08-10","arxiv_id":"2108.04628","repositories_listed":0,"syntology":null},{"url":"/paper/rams-trans-recurrent-attention-multi-scale","slug":"rams-trans-recurrent-attention-multi-scale","title":"RAMS-Trans: Recurrent Attention Multi-scale Transformer forFine-grained Image Recognition","date":"2021-07-17","arxiv_id":"2107.08192","repositories_listed":0,"syntology":null},{"url":"/paper/transformer-with-peak-suppression-and","slug":"transformer-with-peak-suppression-and","title":"Transformer with Peak Suppression and Knowledge Guidance for Fine-grained Image Recognition","date":"2021-07-14","arxiv_id":"2107.06538","repositories_listed":0,"syntology":null},{"url":"/paper/re-rank-coarse-classification-with-local","slug":"re-rank-coarse-classification-with-local","title":"Re-rank Coarse Classification with Local Region Enhanced Features for Fine-Grained Image Recognition","date":"2021-02-19","arxiv_id":"2102.09875","repositories_listed":0,"syntology":null},{"url":null,"slug":"category-specific-semantic-coherency-learning","title":"Category-specific Semantic Coherency Learning for Fine-grained Image Recognition","date":"2020-10-12","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"text-embedded-bilinear-model-for-fine-grained","title":"Text-Embedded Bilinear Model for Fine-Grained Visual Recognition","date":"2020-10-12","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"volumetric-transformer-networks","title":"Volumetric Transformer Networks","date":"2020-07-18","arxiv_id":"2007.09433","repositories_listed":0,"syntology":null},{"url":"/paper/weakly-supervised-fine-grained-image-1","slug":"weakly-supervised-fine-grained-image-1","title":"Weakly Supervised Fine-Grained Image Classification via Guassian Mixture Model Oriented Discriminative Learning","date":"2020-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-image-to-image-transformation","title":"Fine-grained Image-to-Image Transformation towards Visual Recognition","date":"2020-01-12","arxiv_id":"2001.03856","repositories_listed":0,"syntology":null},{"url":null,"slug":"reaps-towards-better-recognition-of-fine","title":"REAPS: Towards Better Recognition of Fine-grained Images by Region Attending and Part Sequencing","date":"2019-08-06","arxiv_id":"1908.01962","repositories_listed":0,"syntology":null},{"url":null,"slug":"compact-approximation-for-polynomial-of","title":"Compact Approximation for Polynomial of Covariance Feature","date":"2019-06-05","arxiv_id":"1906.01851","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-embedded-representation-learning","title":"Knowledge-Embedded Representation Learning for Fine-Grained Image Recognition","date":"2018-07-02","arxiv_id":"1807.00505","repositories_listed":0,"syntology":null},{"url":null,"slug":"deepkspd-learning-kernel-matrix-based-spd","title":"DeepKSPD: Learning Kernel-matrix-based SPD Representation for Fine-grained Image Recognition","date":"2017-11-11","arxiv_id":"1711.04047","repositories_listed":0,"syntology":null},{"url":null,"slug":"look-closer-to-see-better-recurrent-attention","title":"Look Closer to See Better: Recurrent Attention Convolutional Neural Network for Fine-Grained Image Recognition","date":"2017-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"picking-deep-filter-responses-for-fine","title":"Picking Deep Filter Responses for Fine-Grained Image Recognition","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mask-cnn-localizing-parts-and-selecting","title":"Mask-CNN: Localizing Parts and Selecting Descriptors for Fine-Grained Image Recognition","date":"2016-05-23","arxiv_id":"1605.06878","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-image-classification-by","title":"Fine-grained Image Classification by Exploring Bipartite-Graph Labels","date":"2015-12-08","arxiv_id":"1512.02665","repositories_listed":0,"syntology":null}],"syntology_records":8,"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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"papers_where_code_ran":8,"papers_where_code_ran_first_page":"/task/fine-grained-image-recognition/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":"ran","page":1,"of":1,"url":"/task/fine-grained-image-recognition/papers/ran/1","json":"/task/fine-grained-image-recognition/papers/ran/1.json","rows":8}],"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":"a565cb9b6e2490ea7e1f14d505e9b98cb6aa219072d06852f604c533e46da2f5","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}