{"url":"/sota/fine-grained-image-classification-on-cub-200-1","task":{"name":"Fine-Grained Image Classification","url":"/task/fine-grained-image-classification","note":null},"dataset":{"name":"CUB-200-2011","url":"/dataset/cub-200-2011"},"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"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy":"higher"}},"counts":{"rows":30,"rows_with_code":24,"rows_with_paper_page":30,"rows_dated":30,"rows_using_additional_data":3},"rows":[{"rank_in_archive_order":1,"model":"HERBS","metrics":{"Accuracy":"93.1%"},"uses_additional_data":false,"paper_date":"2023-03-11","paper":"/paper/fine-grained-visual-classification-with-high-1","paper_url":"https://arxiv.org/abs/2303.06442v2","paper_title":"Fine-grained Visual Classification with High-temperature Refinement and Background Suppression","code":"https://github.com/chou141253/FGVC-HERBS","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"PIM","metrics":{"Accuracy":"92.8"},"uses_additional_data":true,"paper_date":"2022-02-08","paper":"/paper/a-novel-plug-in-module-for-fine-grained-1","paper_url":"https://arxiv.org/abs/2202.03822v1","paper_title":"A Novel Plug-in Module for Fine-Grained Visual Classification","code":"https://github.com/chou141253/fgvc-pim","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"MDCM","metrics":{"Accuracy":"92.5%"},"uses_additional_data":false,"paper_date":"2025-04-12","paper":"/paper/multi-scale-activation-refinement-and-1","paper_url":"https://arxiv.org/abs/2504.09215v1","paper_title":"Multi-scale Activation, Refinement, and Aggregation: Exploring Diverse Cues for Fine-Grained Bird Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"CAP","metrics":{"Accuracy":"91.8"},"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,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"IELT","metrics":{"Accuracy":"91.8"},"uses_additional_data":false,"paper_date":"2022-06-19","paper":"/paper/0-1-deep-neural-networks-via-block-coordinate","paper_url":"https://arxiv.org/abs/2206.09379v2","paper_title":"0/1 Deep Neural Networks via Block Coordinate Descent","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"SFETrans","metrics":{"Accuracy":"91.8"},"uses_additional_data":false,"paper_date":"2025-06-14","paper":"/paper/structural-feature-enhanced-transformer-for","paper_url":"https://www.sciencedirect.com/science/article/abs/pii/S0031320325006156?dgcid=rss_sd_all","paper_title":"Structural feature enhanced transformer for fine-grained image recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"TransFG","metrics":{"Accuracy":"91.7"},"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,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":2}},{"rank_in_archive_order":8,"model":"SWAG (ViT H/14)","metrics":{"Accuracy":"91.7"},"uses_additional_data":true,"paper_date":"2022-01-20","paper":"/paper/revisiting-weakly-supervised-pre-training-of","paper_url":"https://arxiv.org/abs/2201.08371v2","paper_title":"Revisiting Weakly Supervised Pre-Training of Visual Perception Models","code":"https://github.com/facebookresearch/SWAG","n_code_links":2,"syntology":null},{"rank_in_archive_order":9,"model":"ViT-NeT","metrics":{"Accuracy":"91.7"},"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,"syntology":null},{"rank_in_archive_order":10,"model":"FFVT","metrics":{"Accuracy":"91.6"},"uses_additional_data":false,"paper_date":"2021-07-06","paper":"/paper/feature-fusion-vision-transformer-fine","paper_url":"https://arxiv.org/abs/2107.02341v3","paper_title":"Feature Fusion Vision Transformer for Fine-Grained Visual Categorization","code":"https://github.com/Markin-Wang/FFVT","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"DATL","metrics":{"Accuracy":"91.2"},"uses_additional_data":true,"paper_date":"2020-10-06","paper":"/paper/domain-adaptive-transfer-learning-on-visual","paper_url":"https://arxiv.org/abs/2010.03071v1","paper_title":"Domain Adaptive Transfer Learning on Visual Attention Aware Data Augmentation for Fine-grained Visual Categorization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"CAL","metrics":{"Accuracy":"90.6"},"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,"syntology":{"n_ran":8,"n_unverified":3,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"HOI-Net","metrics":{"Accuracy":"90.02%"},"uses_additional_data":false,"paper_date":"2021-11-13","paper":"/paper/high-order-interaction-for-weakly-supervised","paper_url":"https://www.sciencedirect.com/science/article/abs/pii/S0925231221013060","paper_title":"High-Order-Interaction for weakly supervised Fine-Grained Visual Categorization","code":"https://github.com/puallee/HOI-Net","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"TBMSL-Net","metrics":{"Accuracy":"89.6"},"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,"syntology":null},{"rank_in_archive_order":15,"model":"FBSD","metrics":{"Accuracy":"89.5"},"uses_additional_data":false,"paper_date":"2021-03-04","paper":"/paper/feature-boosting-suppression-and","paper_url":"https://arxiv.org/abs/2103.02782v2","paper_title":"Feature Boosting, Suppression, and Diversification for Fine-Grained Visual Classification","code":"https://github.com/chaomaer/FBSD","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"WS-DAN","metrics":{"Accuracy":"89.4"},"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,"syntology":null},{"rank_in_archive_order":17,"model":"ELP","metrics":{"Accuracy":"88.8"},"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,"syntology":null},{"rank_in_archive_order":18,"model":"MPN-COV","metrics":{"Accuracy":"88.7"},"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,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":1}},{"rank_in_archive_order":19,"model":"FixSENet-154","metrics":{"Accuracy":"88.7"},"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,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":20,"model":"ResNet-50","metrics":{"Accuracy":"88.59"},"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,"syntology":null},{"rank_in_archive_order":21,"model":"DenseNet161+MM+FRL","metrics":{"Accuracy":"88.5"},"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,"syntology":null},{"rank_in_archive_order":22,"model":"LIO","metrics":{"Accuracy":"88.0"},"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,"syntology":null},{"rank_in_archive_order":23,"model":"TASN","metrics":{"Accuracy":"87.9"},"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,"syntology":null},{"rank_in_archive_order":24,"model":"Nts-Net","metrics":{"Accuracy":"87.5"},"uses_additional_data":false,"paper_date":"2020-01-16","paper":"/paper/are-these-birds-similar-learning-branched","paper_url":"https://ieeexplore.ieee.org/document/8960960","paper_title":"Are These Birds Similar: Learning Branched Networks for Fine-grained Representations","code":"https://github.com/nicolalandro/ntsnet-cub200","n_code_links":3,"syntology":null},{"rank_in_archive_order":25,"model":"DFL-CNN","metrics":{"Accuracy":"87.4"},"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,"syntology":null},{"rank_in_archive_order":26,"model":"PC","metrics":{"Accuracy":"86.9"},"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,"syntology":null},{"rank_in_archive_order":27,"model":"MACNN","metrics":{"Accuracy":"86.5"},"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,"syntology":null},{"rank_in_archive_order":28,"model":"Basel.+LSRO","metrics":{"Accuracy":"84.4"},"uses_additional_data":false,"paper_date":"2017-01-26","paper":"/paper/unlabeled-samples-generated-by-gan-improve","paper_url":"http://arxiv.org/abs/1701.07717v5","paper_title":"Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro","code":"https://github.com/layumi/Person-reID_GAN","n_code_links":8,"syntology":null},{"rank_in_archive_order":29,"model":"BYOL+CVSA (ResNet-50)","metrics":{"Accuracy":"77.1"},"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,"syntology":null},{"rank_in_archive_order":30,"model":"Deformable Part Descriptors","metrics":{"Accuracy":"50.98"},"uses_additional_data":false,"paper_date":"2013-12-01","paper":"/paper/deformable-part-descriptors-for-fine-grained","paper_url":"https://openaccess.thecvf.com/content_iccv_2013/papers/Zhang_Deformable_Part_Descriptors_2013_ICCV_paper.pdf","paper_title":"Deformable Part Descriptors for Fine-grained Recognition and Attribute Prediction","code":null,"n_code_links":0,"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,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,795 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6795,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2785},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":["Accuracy"],"entries":[{"paper":"/paper/arxiv-2609-27194","paper_title":"Diverse by Design: Architectural Constraints for Prototype-Based Interpretability","arxiv_id":"2609.27194","model":"DAPL ( D_{1} =16) + FG","row_label":"DAPL ( D_{1} =16) + FG","configuration":null,"configuration_in_model":false,"configuration_not_shown_because":null,"values":{"Accuracy":"81.69"},"date":null,"month_from_arxiv_id":"2026-09","where_in_paper":"Table 1, row “DAPL ( D_{1} =16) + FG”","table_label":"1","table_label_from":"the caption's own label","table_position_1based":1,"caption_head":"Table 1 : Performance on CUB-200-2011 (DenseNet161).","cells":[{"column":"Accuracy","cell_text":"81.69","column_header":"Accuracy / (%)","value":81.69,"table_index_0based":0,"row":8,"col":1}],"code":"repository linked, no samples harvested"}]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N 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).","rows_with_graph_line":5,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":5,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":14,"n_unverified":7,"n_samples":21,"n_pointer_only_licence":5,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":14,"n_unverified":7,"n_samples":21,"n_pointer_only_licence":5,"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"}}}