{"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-visual-recognition","name":"Fine-Grained Visual Recognition","slug":"fine-grained-visual-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":43,"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":9,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/fine-grained-visual-recognition-on-cub-200-1","slug":"fine-grained-visual-recognition-on-cub-200-1","dataset":"CUB-200-2011","dataset_url":"/dataset/cub-200-2011","rows_in_archive":1,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"Selfsynthx","paper_title":"Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data","paper_url":"/paper/enhancing-cognition-and-explainability-of","paper_date":"2025-02-19","arxiv_id":"2502.14044","code_links":[{"title":"sycny/selfsynthx","url":"https://github.com/sycny/selfsynthx"}],"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/enhancing-cognition-and-explainability-of#ran","syntology_url":"https://syntology.ai/paper/2502.14044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.14044"}},"official":{"repos":["sycny/selfsynthx"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}}},{"leaderboard":"/sota/fine-grained-visual-recognition-on-fgvc-2","slug":"fine-grained-visual-recognition-on-fgvc-2","dataset":"FGVC-Aircraft","dataset_url":"/dataset/fgvc-aircraft-1","rows_in_archive":1,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"Selfsynthx","paper_title":"Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data","paper_url":"/paper/enhancing-cognition-and-explainability-of","paper_date":"2025-02-19","arxiv_id":"2502.14044","code_links":[{"title":"sycny/selfsynthx","url":"https://github.com/sycny/selfsynthx"}],"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/enhancing-cognition-and-explainability-of#ran","syntology_url":"https://syntology.ai/paper/2502.14044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.14044"}},"official":{"repos":["sycny/selfsynthx"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}}},{"leaderboard":"/sota/fine-grained-visual-recognition-on-new-plant","slug":"fine-grained-visual-recognition-on-new-plant","dataset":"New Plant Diseases Dataset","dataset_url":"/dataset/new-plant-diseases-dataset","rows_in_archive":1,"metrics":["Accuracy (% )"],"first_row_in_archive_order":{"model":"Selfsynthx","paper_title":"Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data","paper_url":"/paper/enhancing-cognition-and-explainability-of","paper_date":"2025-02-19","arxiv_id":"2502.14044","code_links":[{"title":"sycny/selfsynthx","url":"https://github.com/sycny/selfsynthx"}],"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/enhancing-cognition-and-explainability-of#ran","syntology_url":"https://syntology.ai/paper/2502.14044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.14044"}},"official":{"repos":["sycny/selfsynthx"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}}},{"leaderboard":"/sota/fine-grained-visual-recognition-on-stanford-2","slug":"fine-grained-visual-recognition-on-stanford-2","dataset":"Stanford Dogs","dataset_url":"/dataset/stanford-dogs","rows_in_archive":1,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"Selfsynthx","paper_title":"Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data","paper_url":"/paper/enhancing-cognition-and-explainability-of","paper_date":"2025-02-19","arxiv_id":"2502.14044","code_links":[{"title":"sycny/selfsynthx","url":"https://github.com/sycny/selfsynthx"}],"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/enhancing-cognition-and-explainability-of#ran","syntology_url":"https://syntology.ai/paper/2502.14044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.14044"}},"official":{"repos":["sycny/selfsynthx"],"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"]}}}}],"datasets":[{"url":"/dataset/cub-200-2011","name":"CUB-200-2011","full_name":"Caltech-UCSD Birds-200-2011","num_papers_in_archive":2235},{"url":"/dataset/fgvc-aircraft-1","name":"FGVC-Aircraft","full_name":"","num_papers_in_archive":520},{"url":"/dataset/stanford-dogs","name":"Stanford Dogs","full_name":"Stanford Dogs","num_papers_in_archive":57},{"url":"/dataset/mtl-aqa","name":"MTL-AQA","full_name":"","num_papers_in_archive":33},{"url":"/dataset/webfg-496","name":"WebFG-496","full_name":"","num_papers_in_archive":7},{"url":"/dataset/whoi-plankton","name":"WHOI-Plankton","full_name":"","num_papers_in_archive":6},{"url":"/dataset/new-plant-diseases-dataset","name":"New Plant Diseases Dataset","full_name":"Image dataset containing different healthy and unhealthy crop leaves.","num_papers_in_archive":2},{"url":"/dataset/feathersv1","name":"FeathersV1","full_name":null,"num_papers_in_archive":1},{"url":"/dataset/wikichurches","name":"WikiChurches","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/visual-recognition","name":"Visual 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":43,"tagged_in_all":72,"counts":{"archive_papers_tagged":72,"with_a_code_link":43,"where_syntology_ran_a_sample":15,"not_listed_spam_title":0,"listed":72,"listed_where_code_ran":15,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":10,"every_run_a_failure_of_syntologys_instrument":5,"listed_with_a_run_with_no_instrument_failure":10,"listed_every_run_a_failure_of_syntologys_instrument":5,"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/fashionpedia-ontology-segmentation-and-an","slug":"fashionpedia-ontology-segmentation-and-an","title":"Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset","date":"2020-04-26","arxiv_id":"2004.12276","repositories_listed":8,"syntology":null},{"url":"/paper/bilinear-cnns-for-fine-grained-visual","slug":"bilinear-cnns-for-fine-grained-visual","title":"Bilinear CNNs for Fine-grained Visual Recognition","date":"2015-04-29","arxiv_id":"1504.07889","repositories_listed":4,"syntology":null},{"url":"/paper/deep-cnns-meet-global-covariance-pooling","slug":"deep-cnns-meet-global-covariance-pooling","title":"Deep CNNs Meet Global Covariance Pooling: Better Representation and Generalization","date":"2019-04-15","arxiv_id":"1904.06836","repositories_listed":3,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":2,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/deep-cnns-meet-global-covariance-pooling#ran","syntology_url":"https://syntology.ai/paper/1904.06836","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.06836"}},"official":{"repos":["ZhangLi-CS/GCP_Optimization","jiangtaoxie/MPN-COV","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":2,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/retrieving-similar-e-commerce-images-using","slug":"retrieving-similar-e-commerce-images-using","title":"Retrieving Similar E-Commerce Images Using Deep Learning","date":"2019-01-11","arxiv_id":"1901.03546","repositories_listed":3,"syntology":null},{"url":"/paper/rar-retrieving-and-ranking-augmented-mllms","slug":"rar-retrieving-and-ranking-augmented-mllms","title":"RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition","date":"2024-03-20","arxiv_id":"2403.13805","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/rar-retrieving-and-ranking-augmented-mllms#ran","syntology_url":"https://syntology.ai/paper/2403.13805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13805"}},"official":{"repos":["liuziyu77/rar"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/clip-art-contrastive-pre-training-for-fine-1","slug":"clip-art-contrastive-pre-training-for-fine-1","title":"CLIP-Art: Contrastive Pre-training for Fine-Grained Art Classification","date":"2022-04-29","arxiv_id":"2204.14244","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/clip-art-contrastive-pre-training-for-fine-1#ran","syntology_url":"https://syntology.ai/paper/2204.14244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.14244"}},"official":{"repos":["KeremTurgutlu/clip_art","KeremTurgutlu/self_supervised"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/feathers-dataset-for-fine-grained-visual","slug":"feathers-dataset-for-fine-grained-visual","title":"Feathers dataset for Fine-Grained Visual Categorization","date":"2020-04-18","arxiv_id":"2004.08606","repositories_listed":2,"syntology":null},{"url":"/paper/x-linear-attention-networks-for-image","slug":"x-linear-attention-networks-for-image","title":"X-Linear Attention Networks for Image Captioning","date":"2020-03-31","arxiv_id":"2003.14080","repositories_listed":2,"syntology":null},{"url":"/paper/mildnet-a-lightweight-single-scaled-deep","slug":"mildnet-a-lightweight-single-scaled-deep","title":"MILDNet: A Lightweight Single Scaled Deep Ranking Architecture","date":"2019-03-03","arxiv_id":"1903.00905","repositories_listed":2,"syntology":null},{"url":"/paper/hierarchical-bilinear-pooling-for-fine","slug":"hierarchical-bilinear-pooling-for-fine","title":"Hierarchical Bilinear Pooling for Fine-Grained Visual Recognition","date":"2018-07-26","arxiv_id":"1807.09915","repositories_listed":2,"syntology":null},{"url":"/paper/metric-learning-with-adaptive-density","slug":"metric-learning-with-adaptive-density","title":"Metric Learning with Adaptive Density Discrimination","date":"2015-11-18","arxiv_id":"1511.05939","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/metric-learning-with-adaptive-density#ran","syntology_url":"https://syntology.ai/paper/1511.05939","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.05939"}},"official":null}},{"url":"/paper/enhancing-cognition-and-explainability-of","slug":"enhancing-cognition-and-explainability-of","title":"Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data","date":"2025-02-19","arxiv_id":"2502.14044","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/enhancing-cognition-and-explainability-of#ran","syntology_url":"https://syntology.ai/paper/2502.14044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.14044"}},"official":{"repos":["sycny/selfsynthx"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/analyzing-and-boosting-the-power-of-fine","slug":"analyzing-and-boosting-the-power-of-fine","title":"Analyzing and Boosting the Power of Fine-Grained Visual Recognition for Multi-modal Large Language Models","date":"2025-01-25","arxiv_id":"2501.15140","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"4 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; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/analyzing-and-boosting-the-power-of-fine#ran","syntology_url":"https://syntology.ai/paper/2501.15140","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.15140"}},"official":{"repos":["pku-icst-mipl/finedefics_iclr2025"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/interweaving-insights-high-order-feature","slug":"interweaving-insights-high-order-feature","title":"Interweaving Insights: High-Order Feature Interaction for Fine-Grained Visual Recognition","date":"2024-10-20","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/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/towards-generative-class-prompt-learning-for","slug":"towards-generative-class-prompt-learning-for","title":"Towards Generative Class Prompt Learning for Fine-grained Visual Recognition","date":"2024-09-03","arxiv_id":"2409.01835","repositories_listed":1,"syntology":null},{"url":"/paper/extremely-fine-grained-visual-classification","slug":"extremely-fine-grained-visual-classification","title":"Extremely Fine-Grained Visual Classification over Resembling Glyphs in the Wild","date":"2024-08-25","arxiv_id":"2408.13774","repositories_listed":1,"syntology":null},{"url":"/paper/extract-more-from-less-efficient-fine-grained","slug":"extract-more-from-less-efficient-fine-grained","title":"Extract More from Less: Efficient Fine-Grained Visual Recognition in Low-Data Regimes","date":"2024-06-28","arxiv_id":"2406.19814","repositories_listed":1,"syntology":null},{"url":"/paper/few-shot-classification-of-interactive","slug":"few-shot-classification-of-interactive","title":"Few-Shot Classification of Interactive Activities of Daily Living (InteractADL)","date":"2024-06-03","arxiv_id":"2406.01662","repositories_listed":1,"syntology":null},{"url":"/paper/hgclip-exploring-vision-language-models-with-1","slug":"hgclip-exploring-vision-language-models-with-1","title":"HGCLIP: Exploring Vision-Language Models with Graph Representations for Hierarchical Understanding","date":"2023-11-23","arxiv_id":"2311.14064","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/hgclip-exploring-vision-language-models-with-1#ran","syntology_url":"https://syntology.ai/paper/2311.14064","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.14064"}},"official":{"repos":["richard-peng-xia/HGCLIP"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/dynamic-conceptional-contrastive-learning-for","slug":"dynamic-conceptional-contrastive-learning-for","title":"Dynamic Conceptional Contrastive Learning for Generalized Category Discovery","date":"2023-03-30","arxiv_id":"2303.17393","repositories_listed":1,"syntology":null},{"url":"/paper/learning-common-rationale-to-improve-self","slug":"learning-common-rationale-to-improve-self","title":"Learning Common Rationale to Improve Self-Supervised Representation for Fine-Grained Visual Recognition Problems","date":"2023-03-03","arxiv_id":"2303.01669","repositories_listed":1,"syntology":null},{"url":"/paper/fine-grained-visual-classification-via-2","slug":"fine-grained-visual-classification-via-2","title":"Fine-Grained Visual Classification via Internal Ensemble Learning Transformer","date":"2023-02-13","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/multi-view-active-fine-grained-visual","slug":"multi-view-active-fine-grained-visual","title":"Multi-View Active Fine-Grained Visual Recognition","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/part-guided-relational-transformers-for-fine","slug":"part-guided-relational-transformers-for-fine","title":"Part-guided Relational Transformers for Fine-grained Visual Recognition","date":"2022-12-28","arxiv_id":"2212.13685","repositories_listed":1,"syntology":null},{"url":"/paper/penalizing-the-hard-example-but-not-too-much","slug":"penalizing-the-hard-example-but-not-too-much","title":"Penalizing the Hard Example But Not Too Much: A Strong Baseline for Fine-Grained Visual Classification","date":"2022-11-21","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/improving-fine-grained-visual-recognition-in","slug":"improving-fine-grained-visual-recognition-in","title":"Improving Fine-Grained Visual Recognition in Low Data Regimes via Self-Boosting Attention Mechanism","date":"2022-08-01","arxiv_id":"2208.00617","repositories_listed":1,"syntology":null},{"url":"/paper/memsac-memory-augmented-sample-consistency","slug":"memsac-memory-augmented-sample-consistency","title":"MemSAC: Memory Augmented Sample Consistency for Large Scale Unsupervised Domain Adaptation","date":"2022-07-25","arxiv_id":"2207.12389","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/memsac-memory-augmented-sample-consistency#ran","syntology_url":"https://syntology.ai/paper/2207.12389","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.12389"}},"official":{"repos":["ViLab-UCSD/MemSAC_ECCV2022"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/on-the-eigenvalues-of-global-covariance","slug":"on-the-eigenvalues-of-global-covariance","title":"On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition","date":"2022-05-26","arxiv_id":"2205.13282","repositories_listed":1,"syntology":{"n":17,"n_ran":12,"n_constructed":0,"n_ran_checked":9,"n_instrument":3,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","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"}},"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"]}}},{"url":"/paper/do-vision-language-pretrained-models-learn","slug":"do-vision-language-pretrained-models-learn","title":"Do Vision-Language Pretrained Models Learn Composable Primitive Concepts?","date":"2022-03-31","arxiv_id":"2203.17271","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/do-vision-language-pretrained-models-learn#ran","syntology_url":"https://syntology.ai/paper/2203.17271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.17271"}},"official":{"repos":["tttyuntian/vlm_primitive_concepts"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/generalized-category-discovery","slug":"generalized-category-discovery","title":"Generalized Category Discovery","date":"2022-01-07","arxiv_id":"2201.02609","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/generalized-category-discovery#ran","syntology_url":"https://syntology.ai/paper/2201.02609","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.02609"}},"official":{"repos":["sgvaze/generalized-category-discovery"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/few-shot-keypoint-detection-with-uncertainty","slug":"few-shot-keypoint-detection-with-uncertainty","title":"Few-shot Keypoint Detection with Uncertainty Learning for Unseen Species","date":"2021-12-12","arxiv_id":"2112.06183","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/few-shot-keypoint-detection-with-uncertainty#ran","syntology_url":"https://syntology.ai/paper/2112.06183","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.06183"}},"official":{"repos":["alanlusun/few-shot-keypoint-detection"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"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/exploiting-web-images-for-fine-grained-visual","slug":"exploiting-web-images-for-fine-grained-visual","title":"Exploiting Web Images for Fine-Grained Visual Recognition by Eliminating Noisy Samples and Utilizing Hard Ones","date":"2021-01-23","arxiv_id":"2101.09412","repositories_listed":1,"syntology":null},{"url":"/paper/data-driven-meta-set-based-fine-grained","slug":"data-driven-meta-set-based-fine-grained","title":"Data-driven Meta-set Based Fine-Grained Visual Classification","date":"2020-08-06","arxiv_id":"2008.02438","repositories_listed":1,"syntology":null},{"url":"/paper/ecml-an-ensemble-cascade-metric-learning","slug":"ecml-an-ensemble-cascade-metric-learning","title":"ECML: An Ensemble Cascade Metric Learning Mechanism towards Face Verification","date":"2020-07-11","arxiv_id":"2007.05720","repositories_listed":1,"syntology":null},{"url":"/paper/interpretable-and-accurate-fine-grained","slug":"interpretable-and-accurate-fine-grained","title":"Interpretable and Accurate Fine-grained Recognition via Region Grouping","date":"2020-05-21","arxiv_id":"2005.10411","repositories_listed":1,"syntology":null},{"url":"/paper/multi-objective-matrix-normalization-for-fine","slug":"multi-objective-matrix-normalization-for-fine","title":"Multi-Objective Matrix Normalization for Fine-grained Visual Recognition","date":"2020-03-30","arxiv_id":"2003.13272","repositories_listed":1,"syntology":null},{"url":"/paper/compounding-the-performance-improvements-of","slug":"compounding-the-performance-improvements-of","title":"Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network","date":"2020-01-17","arxiv_id":"2001.06268","repositories_listed":1,"syntology":{"n":11,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/compounding-the-performance-improvements-of#ran","syntology_url":"https://syntology.ai/paper/2001.06268","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.06268"}},"official":{"repos":["clovaai/assembled-cnn"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/meta-reinforced-synthetic-data-for-one-shot-1","slug":"meta-reinforced-synthetic-data-for-one-shot-1","title":"Meta-Reinforced Synthetic Data for One-Shot Fine-Grained Visual Recognition","date":"2019-11-17","arxiv_id":"1911.07164","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/meta-reinforced-synthetic-data-for-one-shot-1#ran","syntology_url":"https://syntology.ai/paper/1911.07164","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.07164"}},"official":{"repos":["apple2373/MetaIRNet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/190600901","slug":"190600901","title":"The iMet Collection 2019 Challenge Dataset","date":"2019-06-03","arxiv_id":"1906.00901","repositories_listed":1,"syntology":null},{"url":"/paper/fine-grained-visual-recognition-with-salient","slug":"fine-grained-visual-recognition-with-salient","title":"Fine-grained visual recognition with salient feature detection","date":"2018-08-12","arxiv_id":"1808.03935","repositories_listed":1,"syntology":null},{"url":"/paper/self-paced-learning-with-adaptive-deep-visual","slug":"self-paced-learning-with-adaptive-deep-visual","title":"Self-Paced Learning with Adaptive Deep Visual Embeddings","date":"2018-07-24","arxiv_id":"1807.09200","repositories_listed":1,"syntology":null},{"url":null,"slug":"figkd-fine-grained-knowledge-distillation-via","title":"FiGKD: Fine-Grained Knowledge Distillation via High-Frequency Detail Transfer","date":"2025-05-17","arxiv_id":"2505.11897","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-vocabulary-free-fine-grained-visual","title":"Efficient Vocabulary-Free Fine-Grained Visual Recognition in the Age of Multimodal LLMs","date":"2025-05-02","arxiv_id":"2505.01064","repositories_listed":0,"syntology":null},{"url":null,"slug":"xr-vlm-cross-relationship-modeling-with-multi","title":"XR-VLM: Cross-Relationship Modeling with Multi-part Prompts and Visual Features for Fine-Grained Recognition","date":"2025-03-10","arxiv_id":"2503.07075","repositories_listed":0,"syntology":null},{"url":null,"slug":"navigating-limitations-with-precision-a-fine","title":"Navigating limitations with precision: A fine-grained ensemble approach to wrist pathology recognition on a limited x-ray dataset","date":"2024-12-18","arxiv_id":"2412.13884","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-learning-discriminative-features-from","title":"On Learning Discriminative Features from Synthesized Data for Self-Supervised Fine-Grained Visual Recognition","date":"2024-07-19","arxiv_id":"2407.14676","repositories_listed":0,"syntology":null},{"url":null,"slug":"lodisc-learning-global-local-discriminative","title":"LoDisc: Learning Global-Local Discriminative Features for Self-Supervised Fine-Grained Visual Recognition","date":"2024-03-06","arxiv_id":"2403.04066","repositories_listed":0,"syntology":null},{"url":null,"slug":"democratizing-fine-grained-visual-recognition","title":"Democratizing Fine-grained Visual Recognition with Large Language Models","date":"2024-01-24","arxiv_id":"2401.13837","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalized-category-discovery-with","title":"Generalized Category Discovery with Clustering Assignment Consistency","date":"2023-10-30","arxiv_id":"2310.19210","repositories_listed":0,"syntology":null},{"url":null,"slug":"detail-reinforcement-diffusion-model","title":"Detail Reinforcement Diffusion Model: Augmentation Fine-Grained Visual Categorization in Few-Shot Conditions","date":"2023-09-15","arxiv_id":"2309.08097","repositories_listed":0,"syntology":null},{"url":null,"slug":"m2former-multi-scale-patch-selection-for-fine","title":"M2Former: Multi-Scale Patch Selection for Fine-Grained Visual Recognition","date":"2023-08-04","arxiv_id":"2308.02161","repositories_listed":0,"syntology":null},{"url":null,"slug":"recent-advances-of-local-mechanisms-in","title":"Recent Advances of Local Mechanisms in Computer Vision: A Survey and Outlook of Recent Work","date":"2023-06-02","arxiv_id":"2306.01929","repositories_listed":0,"syntology":null},{"url":null,"slug":"saliency-guided-mutual-learning-network-for","title":"Robust Saliency-Aware Distillation for Few-shot Fine-grained Visual Recognition","date":"2023-05-12","arxiv_id":"2305.07180","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":"parsing-objects-at-a-finer-granularity-a","title":"Parsing Objects at a Finer Granularity: A Survey","date":"2022-12-28","arxiv_id":"2212.13693","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcing-generated-images-via-meta","title":"Reinforcing Generated Images via Meta-learning for One-Shot Fine-Grained Visual Recognition","date":"2022-04-22","arxiv_id":"2204.10689","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-attention-driven-hierarchical-multi-scale","title":"An attention-driven hierarchical multi-scale representation for visual recognition","date":"2021-10-23","arxiv_id":"2110.12178","repositories_listed":0,"syntology":null},{"url":"/paper/a-free-lunch-from-vit-adaptive-attention","slug":"a-free-lunch-from-vit-adaptive-attention","title":"A free lunch from ViT:Adaptive Attention Multi-scale Fusion Transformer for Fine-grained Visual Recognition","date":"2021-10-04","arxiv_id":"2110.01240","repositories_listed":0,"syntology":null},{"url":null,"slug":"novel-visual-category-discovery-with-dual","title":"Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation","date":"2021-07-07","arxiv_id":"2107.03358","repositories_listed":0,"syntology":null},{"url":null,"slug":"ca-pmg-channel-attention-and-progressive","title":"CA-PMG: Channel attention and progressive multi-granularity training network for fine-grained visual classification","date":"2021-04-21","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/large-scale-visual-food-recognition","slug":"large-scale-visual-food-recognition","title":"Large Scale Visual Food Recognition","date":"2021-03-30","arxiv_id":"2103.16107","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":"spatial-scale-aligned-network-for-fine","title":"Spatial-Scale Aligned Network for Fine-Grained Recognition","date":"2020-01-05","arxiv_id":"2001.01211","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-visual-recognition-with-batch","title":"ACE: Adaptive Confusion Energy for Natural World Data Distribution","date":"2019-10-28","arxiv_id":"1910.12423","repositories_listed":0,"syntology":null},{"url":null,"slug":"coconet-a-collaborative-convolutional-network","title":"CoCoNet: A Collaborative Convolutional Network","date":"2019-01-28","arxiv_id":"1901.09886","repositories_listed":0,"syntology":null},{"url":null,"slug":"grassmann-pooling-as-compact-homogeneous","title":"Grassmann Pooling as Compact Homogeneous Bilinear Pooling for Fine-Grained Visual Classification","date":"2018-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"where-to-focus-deep-attention-based-spatially","title":"Where to Focus: Deep Attention-based Spatially Recurrent Bilinear Networks for Fine-Grained Visual Recognition","date":"2017-09-18","arxiv_id":"1709.05769","repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-intra-class-variance-to-fine","title":"Incorporating Intra-Class Variance to Fine-Grained Visual Recognition","date":"2017-03-01","arxiv_id":"1703.00196","repositories_listed":0,"syntology":null},{"url":"/paper/bilinear-cnn-models-for-fine-grained-visual","slug":"bilinear-cnn-models-for-fine-grained-visual","title":"Bilinear CNN Models for Fine-Grained Visual Recognition","date":"2015-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/whoi-plankton-a-large-scale-fine-grained","slug":"whoi-plankton-a-large-scale-fine-grained","title":"WHOI-Plankton- A Large Scale Fine Grained Visual Recognition Benchmark Dataset for Plankton Classification","date":"2015-10-02","arxiv_id":"1510.00745","repositories_listed":0,"syntology":null}],"syntology_records":15,"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":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/fine-grained-visual-recognition-on-cub-200-1","since_archive":"/sota/fine-grained-visual-recognition-on-cub-200-1#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":15,"papers_where_code_ran_first_page":"/task/fine-grained-visual-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-visual-recognition/papers/ran/1","json":"/task/fine-grained-visual-recognition/papers/ran/1.json","rows":15}],"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":"b45b40d01ac04066ec202344a339af24394535c9db07f9252e6e9971dcf26204","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}