{"url":"/sota/fine-grained-image-classification-on-stanford","task":{"name":"Fine-Grained Image Classification","url":"/task/fine-grained-image-classification","note":null},"dataset":{"name":"Stanford Cars","url":"/dataset/stanford-cars"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Fine-Grained Image Classification** is a task in computer vision where the goal is to classify images into subcategories within a larger category. For example, classifying different species of birds or different types of flowers. This task is considered to be fine-grained because it requires the model to distinguish between subtle differences in visual appearance and patterns, making it more challenging than regular image classification tasks.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Looking for the Devil in the Details](https://arxiv.org/pdf/1903.06150v2.pdf) )</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Accuracy","FLOPS","PARAMS"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy":"higher","FLOPS":"lower","PARAMS":"lower"}},"counts":{"rows":83,"rows_with_code":67,"rows_with_paper_page":83,"rows_dated":83,"rows_using_additional_data":10},"rows":[{"rank_in_archive_order":1,"model":"TResnet-L + PMD","metrics":{"Accuracy":"97.3%"},"uses_additional_data":false,"paper_date":"2024-01-25","paper":"/paper/progressive-multi-task-anti-noise-learning","paper_url":"https://arxiv.org/abs/2401.14336v1","paper_title":"Progressive Multi-task Anti-Noise Learning and Distilling Frameworks for Fine-grained Vehicle Recognition","code":"https://github.com/dichao-liu/anti-noise_fgvr","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"CMAL-Net","metrics":{"Accuracy":"97.1%"},"uses_additional_data":true,"paper_date":"2023-03-22","paper":"/paper/learn-from-each-other-to-classify-better","paper_url":"https://www.sciencedirect.com/science/article/pii/S0031320323002509","paper_title":"Learn from Each Other to Classify Better: Cross-layer Mutual Attention Learning for Fine-grained Visual Classification","code":"https://github.com/Dichao-Liu/CMAL","n_code_links":2,"syntology":null},{"rank_in_archive_order":3,"model":"I2-HOFI","metrics":{"Accuracy":"96.92%"},"uses_additional_data":false,"paper_date":"2024-10-20","paper":"/paper/interweaving-insights-high-order-feature","paper_url":"https://link.springer.com/article/10.1007/s11263-024-02260-y","paper_title":"Interweaving Insights: High-Order Feature Interaction for Fine-Grained Visual Recognition","code":"https://github.com/arindam-1991/i2-hofi","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"TResNet-L + ML-Decoder","metrics":{"Accuracy":"96.41%"},"uses_additional_data":true,"paper_date":"2021-11-25","paper":"/paper/ml-decoder-scalable-and-versatile","paper_url":"https://arxiv.org/abs/2111.12933v2","paper_title":"ML-Decoder: Scalable and Versatile Classification Head","code":"https://github.com/alibaba-miil/ml_decoder","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":3,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"DAT","metrics":{"Accuracy":"96.2%"},"uses_additional_data":true,"paper_date":"2018-11-16","paper":"/paper/domain-adaptive-transfer-learning-with","paper_url":"http://arxiv.org/abs/1811.07056v2","paper_title":"Domain Adaptive Transfer Learning with Specialist Models","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"ALIGN","metrics":{"Accuracy":"96.13%"},"uses_additional_data":true,"paper_date":"2021-02-11","paper":"/paper/scaling-up-visual-and-vision-language","paper_url":"https://arxiv.org/abs/2102.05918v2","paper_title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","code":"https://github.com/facebookresearch/metaclip","n_code_links":5,"syntology":{"n_ran":8,"n_unverified":2,"n_samples":10,"n_pointer_only_licence":9}},{"rank_in_archive_order":7,"model":"SR-GNN","metrics":{"Accuracy":"96.1","FLOPS":"9.8","PARAMS":"30.9"},"uses_additional_data":false,"paper_date":"2022-09-05","paper":"/paper/sr-gnn-spatial-relation-aware-graph-neural","paper_url":"https://arxiv.org/abs/2209.02109v1","paper_title":"SR-GNN: Spatial Relation-aware Graph Neural Network for Fine-Grained Image Categorization","code":"https://github.com/ardhendubehera/sr-gnn","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"EffNet-L2 (SAM)","metrics":{"Accuracy":"95.96%"},"uses_additional_data":true,"paper_date":"2020-10-03","paper":"/paper/sharpness-aware-minimization-for-efficiently-1","paper_url":"https://arxiv.org/abs/2010.01412v3","paper_title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","code":"https://github.com/davda54/sam","n_code_links":18,"syntology":{"n_ran":8,"n_unverified":12,"n_samples":20,"n_pointer_only_licence":6}},{"rank_in_archive_order":9,"model":"SaSPA + CAL","metrics":{"Accuracy":"95.72"},"uses_additional_data":false,"paper_date":"2024-06-20","paper":"/paper/advancing-fine-grained-classification-by","paper_url":"https://arxiv.org/abs/2406.14551v2","paper_title":"Advancing Fine-Grained Classification by Structure and Subject Preserving Augmentation","code":"https://github.com/eyalmichaeli/saspa-aug","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"CAP","metrics":{"Accuracy":"95.7%"},"uses_additional_data":false,"paper_date":"2021-01-17","paper":"/paper/context-aware-attentional-pooling-cap-for","paper_url":"https://arxiv.org/abs/2101.06635v1","paper_title":"Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification","code":"https://github.com/ArdhenduBehera/cap","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"AttNet & AffNet","metrics":{"Accuracy":"95.6%"},"uses_additional_data":false,"paper_date":"2020-05-11","paper":"/paper/fine-grained-visual-classification-with","paper_url":"https://arxiv.org/abs/2005.05123v1","paper_title":"Fine-Grained Visual Classification with Efficient End-to-end Localization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"CSQA-Net","metrics":{"Accuracy":"95.6%"},"uses_additional_data":false,"paper_date":"2024-03-15","paper":"/paper/context-semantic-quality-awareness-network","paper_url":"https://arxiv.org/abs/2403.10298v1","paper_title":"Context-Semantic Quality Awareness Network for Fine-Grained Visual Categorization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":13,"model":"CAL","metrics":{"Accuracy":"95.5%"},"uses_additional_data":false,"paper_date":"2021-08-19","paper":"/paper/counterfactual-attention-learning-for-fine","paper_url":"https://arxiv.org/abs/2108.08728v2","paper_title":"Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification","code":"https://github.com/raoyongming/CAL","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":3,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"CCFR","metrics":{"Accuracy":"95.5%"},"uses_additional_data":false,"paper_date":"2021-02-19","paper":"/paper/re-rank-coarse-classification-with-local","paper_url":"https://arxiv.org/abs/2102.09875v1","paper_title":"Re-rank Coarse Classification with Local Region Enhanced Features for Fine-Grained Image Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":15,"model":"MPSA","metrics":{"Accuracy":"95.4%"},"uses_additional_data":false,"paper_date":"2024-08-16","paper":"/paper/multi-granularity-part-sampling-attention-for","paper_url":"https://ieeexplore.ieee.org/document/10638479","paper_title":"Multi-Granularity Part Sampling Attention for Fine-Grained Visual Classification","code":"https://github.com/mobulan/MPSA","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"Inceptionv4","metrics":{"Accuracy":"95.35%"},"uses_additional_data":false,"paper_date":"2021-07-19","paper":"/paper/non-binary-deep-transfer-learning-for","paper_url":"https://arxiv.org/abs/2107.08585v2","paper_title":"Non-binary deep transfer learning for image classification","code":"https://github.com/XuyangSHEN/Non-binary-deep-transfer-learning-for-image-classification","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"API-Net","metrics":{"Accuracy":"95.3%"},"uses_additional_data":false,"paper_date":"2020-02-24","paper":"/paper/learning-attentive-pairwise-interaction-for","paper_url":"https://arxiv.org/abs/2002.10191v1","paper_title":"Learning Attentive Pairwise Interaction for Fine-Grained Classification","code":"https://github.com/PeiqinZhuang/API-Net","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":18,"model":"DCAL","metrics":{"Accuracy":"95.3%"},"uses_additional_data":false,"paper_date":"2022-05-04","paper":"/paper/dual-cross-attention-learning-for-fine","paper_url":"https://arxiv.org/abs/2205.02151v1","paper_title":"Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":19,"model":"PART","metrics":{"Accuracy":"95.3%"},"uses_additional_data":false,"paper_date":"2022-12-28","paper":"/paper/part-guided-relational-transformers-for-fine","paper_url":"https://arxiv.org/abs/2212.13685v1","paper_title":"Part-guided Relational Transformers for Fine-grained Visual Recognition","code":"https://github.com/icvteam/part","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"DenseNet161+MM+FRL","metrics":{"Accuracy":"95.2%"},"uses_additional_data":false,"paper_date":"2020-11-22","paper":"/paper/towards-class-specific-unit","paper_url":"https://arxiv.org/abs/2011.10951v2","paper_title":"Learning Class Unique Features in Fine-Grained Visual Classification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":21,"model":"PMG","metrics":{"Accuracy":"95.1%"},"uses_additional_data":false,"paper_date":"2020-03-08","paper":"/paper/fine-grained-visual-classification-via","paper_url":"https://arxiv.org/abs/2003.03836v3","paper_title":"Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches","code":"https://github.com/PRIS-CV/PMG-Progressive-Multi-Granularity-Training","n_code_links":5,"syntology":{"n_ran":2,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":22,"model":"Multi Granularity","metrics":{"Accuracy":"95.1%"},"uses_additional_data":false,"paper_date":"2020-11-18","paper":"/paper/your-labrador-is-my-dog-fine-grained-or-not","paper_url":"https://arxiv.org/abs/2011.09040v3","paper_title":"Your \"Flamingo\" is My \"Bird\": Fine-Grained, or Not","code":"https://github.com/PRIS-CV/Fine-Grained-or-Not","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"TBMSL-Net","metrics":{"Accuracy":"95.0%"},"uses_additional_data":false,"paper_date":"2020-03-20","paper":"/paper/three-branch-and-mutil-scale-learning-for","paper_url":"https://arxiv.org/abs/2003.09150v3","paper_title":"Multi-branch and Multi-scale Attention Learning for Fine-Grained Visual Categorization","code":"https://github.com/ZF1044404254/TBMSL-Net","n_code_links":6,"syntology":null},{"rank_in_archive_order":24,"model":"ELoPE","metrics":{"Accuracy":"95.0%"},"uses_additional_data":false,"paper_date":"2019-11-17","paper":"/paper/elope-fine-grained-visual-classification-with","paper_url":"https://arxiv.org/abs/1911.07344v1","paper_title":"ELoPE: Fine-Grained Visual Classification with Efficient Localization, Pooling and Embedding","code":"https://github.com/rwth-i6/fgvc/tree/master/elope_torch","n_code_links":1,"syntology":null},{"rank_in_archive_order":25,"model":"ViT-NeT (SwinV2-B)","metrics":{"Accuracy":"95.0%"},"uses_additional_data":false,"paper_date":"2022-07-17","paper":"/paper/vit-net-interpretable-vision-transformers","paper_url":"https://proceedings.mlr.press/v162/kim22g/kim22g.pdf","paper_title":"ViT-NeT: Interpretable Vision Transformers with Neural Tree Decoder","code":"https://github.com/jumpsnack/ViT-NeT","n_code_links":1,"syntology":null},{"rank_in_archive_order":26,"model":"AFTrans","metrics":{"Accuracy":"95.0%"},"uses_additional_data":false,"paper_date":"2021-10-04","paper":"/paper/a-free-lunch-from-vit-adaptive-attention","paper_url":"https://arxiv.org/abs/2110.01240v2","paper_title":"A free lunch from ViT:Adaptive Attention Multi-scale Fusion Transformer for Fine-grained Visual Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":27,"model":"DB","metrics":{"Accuracy":"94.9%"},"uses_additional_data":false,"paper_date":"2019-12-14","paper":"/paper/fine-grained-recognition-accounting-for","paper_url":"https://arxiv.org/abs/1912.06842v1","paper_title":"Fine-grained Recognition: Accounting for Subtle Differences between Similar Classes","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":28,"model":"Attribute Mix+","metrics":{"Accuracy":"94.9%"},"uses_additional_data":false,"paper_date":"2020-04-06","paper":"/paper/attribute-mix-semantic-data-augmentation-for","paper_url":"https://arxiv.org/abs/2004.02684v2","paper_title":"Attribute Mix: Semantic Data Augmentation for Fine Grained Recognition","code":"https://github.com/Westlake-AI/openmixup","n_code_links":1,"syntology":null},{"rank_in_archive_order":29,"model":"AutoAugment","metrics":{"Accuracy":"94.8%"},"uses_additional_data":false,"paper_date":"2018-05-24","paper":"/paper/autoaugment-learning-augmentation-policies","paper_url":"http://arxiv.org/abs/1805.09501v3","paper_title":"AutoAugment: Learning Augmentation Policies from Data","code":"https://github.com/tensorflow/models/tree/master/research/autoaugment","n_code_links":33,"syntology":{"n_ran":6,"n_unverified":37,"n_samples":43,"n_pointer_only_licence":2}},{"rank_in_archive_order":30,"model":"BCN","metrics":{"Accuracy":"94.8%"},"uses_additional_data":false,"paper_date":"2019-10-28","paper":"/paper/fine-grained-visual-classification-with-batch","paper_url":"https://arxiv.org/abs/1910.12423","paper_title":"Fine-Grained Visual Classification with Batch Confusion Norm","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":31,"model":"DF-GMM","metrics":{"Accuracy":"94.8%"},"uses_additional_data":false,"paper_date":"2020-06-01","paper":"/paper/weakly-supervised-fine-grained-image-1","paper_url":"http://openaccess.thecvf.com/content_CVPR_2020/html/Wang_Weakly_Supervised_Fine-Grained_Image_Classification_via_Guassian_Mixture_Model_Oriented_CVPR_2020_paper.html","paper_title":"Weakly Supervised Fine-Grained Image Classification via Guassian Mixture Model Oriented Discriminative Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":32,"model":"TransFG","metrics":{"Accuracy":"94.8%"},"uses_additional_data":false,"paper_date":"2021-03-14","paper":"/paper/transfg-a-transformer-architecture-for-fine","paper_url":"https://arxiv.org/abs/2103.07976v5","paper_title":"TransFG: A Transformer Architecture for Fine-grained Recognition","code":"https://github.com/TACJu/TransFG","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":2}},{"rank_in_archive_order":33,"model":"CRA-CNN","metrics":{"Accuracy":"94.8%"},"uses_additional_data":false,"paper_date":"2020-09-08","paper":"/paper/contrastively-reinforced-attention","paper_url":"https://www.bmvc2020-conference.com/conference/papers/paper_0656.html","paper_title":"Contrastively-reinforced Attention Convolutional Neural Network for Fine-grained Image Recognition","code":"https://github.com/Dichao-Liu/CRA-CNN","n_code_links":1,"syntology":null},{"rank_in_archive_order":34,"model":"S3N","metrics":{"Accuracy":"94.7%"},"uses_additional_data":false,"paper_date":"2019-10-01","paper":"/paper/selective-sparse-sampling-for-fine-grained","paper_url":"http://openaccess.thecvf.com/content_ICCV_2019/html/Ding_Selective_Sparse_Sampling_for_Fine-Grained_Image_Recognition_ICCV_2019_paper.html","paper_title":"Selective Sparse Sampling for Fine-Grained Image Recognition","code":"https://github.com/Yao-DD/S3N","n_code_links":1,"syntology":null},{"rank_in_archive_order":35,"model":"EfficientNet-B7","metrics":{"Accuracy":"94.7%"},"uses_additional_data":false,"paper_date":"2019-05-28","paper":"/paper/efficientnet-rethinking-model-scaling-for","paper_url":"https://arxiv.org/abs/1905.11946v5","paper_title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","code":"https://github.com/ultralytics/yolov5","n_code_links":144,"syntology":{"n_ran":171,"n_unverified":131,"n_samples":302,"n_pointer_only_licence":112}},{"rank_in_archive_order":36,"model":"Grafit (RegNet-8GF)","metrics":{"Accuracy":"94.7%"},"uses_additional_data":false,"paper_date":"2020-11-25","paper":"/paper/grafit-learning-fine-grained-image","paper_url":"https://arxiv.org/abs/2011.12982v1","paper_title":"Grafit: Learning fine-grained image representations with coarse labels","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":37,"model":"GPipe","metrics":{"Accuracy":"94.6%"},"uses_additional_data":false,"paper_date":"2018-11-16","paper":"/paper/gpipe-efficient-training-of-giant-neural","paper_url":"https://arxiv.org/abs/1811.06965v5","paper_title":"GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism","code":"https://github.com/tensorflow/lingvo","n_code_links":13,"syntology":{"n_ran":1,"n_unverified":24,"n_samples":25,"n_pointer_only_licence":16}},{"rank_in_archive_order":38,"model":"Cross-X","metrics":{"Accuracy":"94.6%"},"uses_additional_data":false,"paper_date":"2019-09-10","paper":"/paper/cross-x-learning-for-fine-grained-visual","paper_url":"https://arxiv.org/abs/1909.04412v1","paper_title":"Cross-X Learning for Fine-Grained Visual Categorization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":39,"model":"ACNet","metrics":{"Accuracy":"94.6%"},"uses_additional_data":false,"paper_date":"2019-09-25","paper":"/paper/attention-convolutional-binary-neural-tree","paper_url":"https://arxiv.org/abs/1909.11378v2","paper_title":"Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization","code":"https://github.com/FlyingMoon-GitHub/ACNet","n_code_links":2,"syntology":null},{"rank_in_archive_order":40,"model":"SEB+EfficientNet-B5","metrics":{"Accuracy":"94.6%"},"uses_additional_data":false,"paper_date":"2022-05-26","paper":"/paper/on-the-eigenvalues-of-global-covariance","paper_url":"https://arxiv.org/abs/2205.13282v1","paper_title":"On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition","code":"https://github.com/KingJamesSong/DifferentiableSVD","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":14,"n_samples":17,"n_pointer_only_licence":0}},{"rank_in_archive_order":41,"model":"PCA","metrics":{"Accuracy":"94.6%"},"uses_additional_data":false,"paper_date":"2021-01-21","paper":"/paper/progressive-co-attention-network-for-fine","paper_url":"https://arxiv.org/abs/2101.08527v2","paper_title":"Progressive Co-Attention Network for Fine-grained Visual Classification","code":"https://github.com/PRIS-CV/PCA-Net","n_code_links":1,"syntology":null},{"rank_in_archive_order":42,"model":"WS-DAN","metrics":{"Accuracy":"94.5%"},"uses_additional_data":false,"paper_date":"2019-01-26","paper":"/paper/see-better-before-looking-closer-weakly","paper_url":"http://arxiv.org/abs/1901.09891v2","paper_title":"See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification","code":"https://github.com/wvinzh/WS_DAN_PyTorch","n_code_links":4,"syntology":null},{"rank_in_archive_order":43,"model":"CIN","metrics":{"Accuracy":"94.5%"},"uses_additional_data":false,"paper_date":"2020-03-11","paper":"/paper/channel-interaction-networks-for-fine-grained-1","paper_url":"https://arxiv.org/abs/2003.05235v1","paper_title":"Channel Interaction Networks for Fine-Grained Image Categorization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":44,"model":"LIO/ResNet-50 (multi-stage)","metrics":{"Accuracy":"94.5%"},"uses_additional_data":false,"paper_date":"2020-03-31","paper":"/paper/look-into-object-self-supervised-structure","paper_url":"https://arxiv.org/abs/2003.14142v1","paper_title":"Look-into-Object: Self-supervised Structure Modeling for Object Recognition","code":"https://github.com/JDAI-CV/DCL","n_code_links":2,"syntology":null},{"rank_in_archive_order":45,"model":"Grad-CAM","metrics":{"Accuracy":"94.41%"},"uses_additional_data":false,"paper_date":"2021-01-24","paper":"/paper/grad-cam-guided-channel-spatial-attention","paper_url":"https://arxiv.org/abs/2101.09666v1","paper_title":"Grad-CAM guided channel-spatial attention module for fine-grained visual classification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":46,"model":"FixSENet-154","metrics":{"Accuracy":"94.4%"},"uses_additional_data":false,"paper_date":"2019-06-14","paper":"/paper/fixing-the-train-test-resolution-discrepancy","paper_url":"https://arxiv.org/abs/1906.06423v4","paper_title":"Fixing the train-test resolution discrepancy","code":"https://github.com/facebookresearch/FixRes","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":47,"model":"Assemble-ResNet-FGVC-50","metrics":{"Accuracy":"94.4%"},"uses_additional_data":false,"paper_date":"2020-01-17","paper":"/paper/compounding-the-performance-improvements-of","paper_url":"https://arxiv.org/abs/2001.06268v2","paper_title":"Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network","code":"https://github.com/clovaai/assembled-cnn","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":10,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":48,"model":"MC Loss (B-CNN)","metrics":{"Accuracy":"94.4%"},"uses_additional_data":false,"paper_date":"2020-02-11","paper":"/paper/the-devil-is-in-the-channels-mutual-channel","paper_url":"https://arxiv.org/abs/2002.04264v3","paper_title":"The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification","code":"https://github.com/frgfm/Holocron","n_code_links":3,"syntology":{"n_ran":2,"n_unverified":3,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":49,"model":"ELP","metrics":{"Accuracy":"94.2"},"uses_additional_data":false,"paper_date":"2022-01-01","paper":"/paper/a-simple-episodic-linear-probe-improves","paper_url":"http://openaccess.thecvf.com//content/CVPR2022/html/Liang_A_Simple_Episodic_Linear_Probe_Improves_Visual_Recognition_in_the_CVPR_2022_paper.html","paper_title":"A Simple Episodic Linear Probe Improves Visual Recognition in the Wild","code":"https://github.com/JDAI-CV/DCL","n_code_links":2,"syntology":null},{"rank_in_archive_order":50,"model":"MHEM (strong ResNet50 baseline)","metrics":{"Accuracy":"94.2%"},"uses_additional_data":false,"paper_date":"2022-11-21","paper":"/paper/penalizing-the-hard-example-but-not-too-much","paper_url":"https://ieeexplore.ieee.org/abstract/document/9956020","paper_title":"Penalizing the Hard Example But Not Too Much: A Strong Baseline for Fine-Grained Visual Classification","code":"https://github.com/akira-l/mhem","n_code_links":1,"syntology":null},{"rank_in_archive_order":51,"model":"RDNet-S (224 res, IN-1K pretrained)","metrics":{"Accuracy":"94.2%","FLOPS":"8.7G","PARAMS":"50M"},"uses_additional_data":false,"paper_date":"2024-03-28","paper":"/paper/densenets-reloaded-paradigm-shift-beyond","paper_url":"https://arxiv.org/abs/2403.19588v2","paper_title":"DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs","code":"https://github.com/huggingface/pytorch-image-models","n_code_links":3,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":52,"model":"RDNet-L (224 res, IN-1K pretrained)","metrics":{"Accuracy":"94.2%","FLOPS":"34.7G","PARAMS":"186M"},"uses_additional_data":false,"paper_date":"2024-03-28","paper":"/paper/densenets-reloaded-paradigm-shift-beyond","paper_url":"https://arxiv.org/abs/2403.19588v2","paper_title":"DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs","code":"https://github.com/huggingface/pytorch-image-models","n_code_links":3,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":53,"model":"RDNet-B (224 res, IN-1K pretrained)","metrics":{"Accuracy":"94.1%","FLOPS":"15.4G","PARAMS":"87M"},"uses_additional_data":false,"paper_date":"2024-03-28","paper":"/paper/densenets-reloaded-paradigm-shift-beyond","paper_url":"https://arxiv.org/abs/2403.19588v2","paper_title":"DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs","code":"https://github.com/huggingface/pytorch-image-models","n_code_links":3,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":54,"model":"GCL","metrics":{"Accuracy":"94.0%"},"uses_additional_data":false,"paper_date":"2020-02-14","paper":"/paper/graph-propagation-based-correlation-learning","paper_url":"https://www.aaai.org/Papers/AAAI/2020GB/AAAI-WangZ.4646.pdf","paper_title":"Graph-propagation based Correlation Learning for Weakly Supervised Fine-grained Image Classification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":55,"model":"SEF","metrics":{"Accuracy":"94.0%"},"uses_additional_data":false,"paper_date":"2020-06-24","paper":"/paper/learning-semantically-enhanced-feature-for","paper_url":"https://arxiv.org/abs/2006.13457v3","paper_title":"Learning Semantically Enhanced Feature for Fine-Grained Image Classification","code":"https://github.com/cswluo/SEF","n_code_links":2,"syntology":null},{"rank_in_archive_order":56,"model":"AENet","metrics":{"Accuracy":"94.0%"},"uses_additional_data":false,"paper_date":"2021-03-01","paper":"/paper/alignment-enhancement-network-for-fine","paper_url":"https://dl.acm.org/doi/abs/10.1145/3446208","paper_title":"Alignment Enhancement Network for Fine-grained Visual Categorization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":57,"model":"NTS-Net (K=4)","metrics":{"Accuracy":"93.9%"},"uses_additional_data":false,"paper_date":"2018-09-02","paper":"/paper/learning-to-navigate-for-fine-grained","paper_url":"http://arxiv.org/abs/1809.00287v1","paper_title":"Learning to Navigate for Fine-grained Classification","code":"https://github.com/osmr/imgclsmob","n_code_links":12,"syntology":{"n_ran":3,"n_unverified":6,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":58,"model":"Bamboo (ViT-B/16)","metrics":{"Accuracy":"93.9%"},"uses_additional_data":true,"paper_date":"2022-03-15","paper":"/paper/bamboo-building-mega-scale-vision-dataset","paper_url":"https://arxiv.org/abs/2203.07845v2","paper_title":"Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy","code":"https://github.com/zhangyuanhan-ai/bamboo","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":59,"model":"RDNet-T (224 res, IN-1K pretrained)","metrics":{"Accuracy":"93.9%","FLOPS":"5.0G","PARAMS":"24M"},"uses_additional_data":false,"paper_date":"2024-03-28","paper":"/paper/densenets-reloaded-paradigm-shift-beyond","paper_url":"https://arxiv.org/abs/2403.19588v2","paper_title":"DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs","code":"https://github.com/huggingface/pytorch-image-models","n_code_links":3,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":60,"model":"DFL-CNN","metrics":{"Accuracy":"93.8%"},"uses_additional_data":false,"paper_date":"2016-11-29","paper":"/paper/learning-a-discriminative-filter-bank-within","paper_url":"http://arxiv.org/abs/1611.09932v3","paper_title":"Learning a Discriminative Filter Bank within a CNN for Fine-grained Recognition","code":"https://github.com/jobinkv/Ongoing","n_code_links":1,"syntology":null},{"rank_in_archive_order":61,"model":"TASN","metrics":{"Accuracy":"93.8%"},"uses_additional_data":false,"paper_date":"2019-03-14","paper":"/paper/looking-for-the-devil-in-the-details-learning","paper_url":"https://arxiv.org/abs/1903.06150v2","paper_title":"Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognition","code":"https://github.com/researchmm/tasn","n_code_links":1,"syntology":null},{"rank_in_archive_order":62,"model":"ViT-L (attn finetune)","metrics":{"Accuracy":"93.8%"},"uses_additional_data":true,"paper_date":"2022-03-18","paper":"/paper/three-things-everyone-should-know-about","paper_url":"https://arxiv.org/abs/2203.09795v1","paper_title":"Three things everyone should know about Vision Transformers","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":8,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":63,"model":"AutoFormer-S | 384","metrics":{"Accuracy":"93.4%"},"uses_additional_data":false,"paper_date":"2021-07-01","paper":"/paper/autoformer-searching-transformers-for-visual","paper_url":"https://arxiv.org/abs/2107.00651v1","paper_title":"AutoFormer: Searching Transformers for Visual Recognition","code":"https://github.com/microsoft/AutoML","n_code_links":2,"syntology":null},{"rank_in_archive_order":64,"model":"MPN-COV","metrics":{"Accuracy":"93.3%"},"uses_additional_data":false,"paper_date":"2017-12-04","paper":"/paper/towards-faster-training-of-global-covariance","paper_url":"http://arxiv.org/abs/1712.01034v2","paper_title":"Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalization","code":"https://github.com/osmr/imgclsmob","n_code_links":4,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":1}},{"rank_in_archive_order":65,"model":"DeiT-B","metrics":{"Accuracy":"93.3%","PARAMS":"86M"},"uses_additional_data":false,"paper_date":"2020-12-23","paper":"/paper/training-data-efficient-image-transformers","paper_url":"https://arxiv.org/abs/2012.12877v2","paper_title":"Training data-efficient image transformers & distillation through attention","code":"https://github.com/huggingface/transformers","n_code_links":40,"syntology":{"n_ran":12,"n_unverified":7,"n_samples":19,"n_pointer_only_licence":3}},{"rank_in_archive_order":66,"model":"ResNet101-swp","metrics":{"Accuracy":"93.1%"},"uses_additional_data":false,"paper_date":"2017-04-04","paper":"/paper/deep-cnns-with-spatially-weighted-pooling-for","paper_url":"https://ieeexplore.ieee.org/document/7891907","paper_title":"Deep CNNs With Spatially Weighted Pooling for Fine-Grained Car Recognition","code":"https://github.com/duongttr/SWP","n_code_links":1,"syntology":null},{"rank_in_archive_order":67,"model":"MAMC","metrics":{"Accuracy":"93.0%"},"uses_additional_data":false,"paper_date":"2018-06-14","paper":"/paper/multi-attention-multi-class-constraint-for","paper_url":"http://arxiv.org/abs/1806.05372v1","paper_title":"Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition","code":"https://github.com/xcnkx/fine_grained_classification","n_code_links":1,"syntology":null},{"rank_in_archive_order":68,"model":"NAT-M4","metrics":{"Accuracy":"92.9%","FLOPS":"369M","PARAMS":"3.7M"},"uses_additional_data":false,"paper_date":"2020-05-12","paper":"/paper/neural-architecture-transfer","paper_url":"https://arxiv.org/abs/2005.05859v2","paper_title":"Neural Architecture Transfer","code":"https://github.com/human-analysis/neural-architecture-transfer","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":69,"model":"PC-DenseNet-161","metrics":{"Accuracy":"92.86%"},"uses_additional_data":false,"paper_date":"2017-05-22","paper":"/paper/pairwise-confusion-for-fine-grained-visual","paper_url":"http://arxiv.org/abs/1705.08016v3","paper_title":"Pairwise Confusion for Fine-Grained Visual Classification","code":"https://github.com/abhimanyudubey/confusion","n_code_links":1,"syntology":null},{"rank_in_archive_order":70,"model":"MACNN","metrics":{"Accuracy":"92.8"},"uses_additional_data":false,"paper_date":"2017-10-01","paper":"/paper/learning-multi-attention-convolutional-neural","paper_url":"http://openaccess.thecvf.com/content_iccv_2017/html/Zheng_Learning_Multi-Attention_Convolutional_ICCV_2017_paper.html","paper_title":"Learning Multi-Attention Convolutional Neural Network for Fine-Grained Image Recognition","code":"https://github.com/minfengUCAS/Muti-Attention-CNN","n_code_links":3,"syntology":null},{"rank_in_archive_order":71,"model":"ResNet50 (A1)","metrics":{"Accuracy":"92.7%","FLOPS":"4.1B","PARAMS":"24M"},"uses_additional_data":false,"paper_date":"2021-10-01","paper":"/paper/resnet-strikes-back-an-improved-training","paper_url":"https://arxiv.org/abs/2110.00476v1","paper_title":"ResNet strikes back: An improved training procedure in timm","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":14,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":72,"model":"NAT-M3","metrics":{"Accuracy":"92.6%","FLOPS":"289M","PARAMS":"3.5M"},"uses_additional_data":false,"paper_date":"2020-05-12","paper":"/paper/neural-architecture-transfer","paper_url":"https://arxiv.org/abs/2005.05859v2","paper_title":"Neural Architecture Transfer","code":"https://github.com/human-analysis/neural-architecture-transfer","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":73,"model":"CS-Parts","metrics":{"Accuracy":"92.5%"},"uses_additional_data":false,"paper_date":"2019-09-16","paper":"/paper/classification-specific-parts-for-improving","paper_url":"https://arxiv.org/abs/1909.07075v1","paper_title":"Classification-Specific Parts for Improving Fine-Grained Visual Categorization","code":"https://github.com/DiKorsch/l1_parts","n_code_links":2,"syntology":null},{"rank_in_archive_order":74,"model":"CS-Part","metrics":{"Accuracy":"92.5%"},"uses_additional_data":false,"paper_date":"2019-09-16","paper":"/paper/classification-specific-parts-for-improving","paper_url":"https://arxiv.org/abs/1909.07075v1","paper_title":"Classification-Specific Parts for Improving Fine-Grained Visual Categorization","code":"https://github.com/DiKorsch/l1_parts","n_code_links":2,"syntology":null},{"rank_in_archive_order":75,"model":"NAT-M2","metrics":{"Accuracy":"92.2%","FLOPS":"222M","PARAMS":"2.7M"},"uses_additional_data":false,"paper_date":"2020-05-12","paper":"/paper/neural-architecture-transfer","paper_url":"https://arxiv.org/abs/2005.05859v2","paper_title":"Neural Architecture Transfer","code":"https://github.com/human-analysis/neural-architecture-transfer","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":76,"model":"ResNet-50","metrics":{"Accuracy":"91.06%"},"uses_additional_data":false,"paper_date":"2023-08-25","paper":"/paper/advisingnets-learning-to-distinguish-correct","paper_url":"https://arxiv.org/abs/2308.13651v5","paper_title":"PCNN: Probable-Class Nearest-Neighbor Explanations Improve Fine-Grained Image Classification Accuracy for AIs and Humans","code":"https://github.com/giangnguyen2412/PCNN-src-code-TMRL2024","n_code_links":2,"syntology":null},{"rank_in_archive_order":77,"model":"NAT-M1","metrics":{"Accuracy":"90.9%","FLOPS":"165M","PARAMS":"2.4M"},"uses_additional_data":false,"paper_date":"2020-05-12","paper":"/paper/neural-architecture-transfer","paper_url":"https://arxiv.org/abs/2005.05859v2","paper_title":"Neural Architecture Transfer","code":"https://github.com/human-analysis/neural-architecture-transfer","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":78,"model":"BYOL+CVSA (ResNet-50)","metrics":{"Accuracy":"89.76%"},"uses_additional_data":false,"paper_date":"2021-06-30","paper":"/paper/align-yourself-self-supervised-pre-training","paper_url":"https://arxiv.org/abs/2106.15788v4","paper_title":"Exploring Localization for Self-supervised Fine-grained Contrastive Learning","code":"https://github.com/Westlake-AI/openmixup","n_code_links":1,"syntology":null},{"rank_in_archive_order":79,"model":"ResMLP-24","metrics":{"Accuracy":"89.5%"},"uses_additional_data":false,"paper_date":"2021-05-07","paper":"/paper/resmlp-feedforward-networks-for-image","paper_url":"https://arxiv.org/abs/2105.03404v2","paper_title":"ResMLP: Feedforward networks for image classification with data-efficient training","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":19,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":80,"model":"MPFG + CLIP","metrics":{"Accuracy":"86.79"},"uses_additional_data":true,"paper_date":"2023-08-08","paper":"/paper/multiscale-patch-based-feature-graphs-for","paper_url":"https://www.sciencedirect.com/science/article/pii/S0957417423016184","paper_title":"Multiscale patch-based feature graphs for image classification","code":"https://github.com/mvtodescato/MultiscaleGraphFeatures","n_code_links":1,"syntology":null},{"rank_in_archive_order":81,"model":"ResMLP-12","metrics":{"Accuracy":"84.6%"},"uses_additional_data":false,"paper_date":"2021-05-07","paper":"/paper/resmlp-feedforward-networks-for-image","paper_url":"https://arxiv.org/abs/2105.03404v2","paper_title":"ResMLP: Feedforward networks for image classification with data-efficient training","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":19,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":82,"model":"SEER (RegNet10B)","metrics":{"Accuracy":"68.03%"},"uses_additional_data":true,"paper_date":"2022-02-16","paper":"/paper/vision-models-are-more-robust-and-fair-when","paper_url":"https://arxiv.org/abs/2202.08360v2","paper_title":"Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision","code":"https://github.com/facebookresearch/vissl","n_code_links":1,"syntology":null},{"rank_in_archive_order":83,"model":"MANO-tiny","metrics":{"Accuracy":"65.68"},"uses_additional_data":true,"paper_date":"2025-07-03","paper":"/paper/linear-attention-with-global-context-a-1","paper_url":"https://arxiv.org/abs/2507.02748v1","paper_title":"Linear Attention with Global Context: A Multipole Attention Mechanism for Vision and Physics","code":"https://github.com/AlexColagrande/MANO","n_code_links":1,"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 6,264 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":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"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":32,"rows_with_any_sample_ran":24,"distinct_papers_with_graph_line":25,"distinct_papers_with_any_sample_ran":20,"samples_over_distinct_papers":{"n_ran":243,"n_unverified":271,"n_samples":514,"n_pointer_only_licence":159,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":254,"n_unverified":279,"n_samples":533,"n_pointer_only_licence":162,"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"}}}