{"task":"Multi-Label Classification","dataset":"MS-COCO","metric_names":["mAP"],"rows":[{"id":759300,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"Diffusion-Based Cross-Modal Feature Extr","metrics":{"mAP":"98.6"},"paper_url":"https://paperswithcode.com/paper/diffusion-based-cross-modal-feature-extraction-for-multi-label-classification","paper_title":"Diffusion-Based Cross-Modal Feature Extraction for Multi-Label Classification","paper_date":"2025-09-19","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]},{"id":51425,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"ADDS(ViT-L-336, resolution 1344)","metrics":{"mAP":"93.54"},"paper_url":"https://arxiv.org/abs/2208.09562v2","paper_title":"Open Vocabulary Multi-Label Classification with Dual-Modal Decoder on Aligned Visual-Textual Features","paper_date":"2022-08-19","code_links":[],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51426,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"ADDS(ViT-L-336, resolution 640)","metrics":{"mAP":"93.41"},"paper_url":"https://arxiv.org/abs/2208.09562v2","paper_title":"Open Vocabulary Multi-Label Classification with Dual-Modal Decoder on Aligned Visual-Textual Features","paper_date":"2022-08-19","code_links":[],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51427,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"ADDS(ViT-L-336, resolution 336)","metrics":{"mAP":"91.76"},"paper_url":"https://arxiv.org/abs/2208.09562v2","paper_title":"Open Vocabulary Multi-Label Classification with Dual-Modal Decoder on Aligned Visual-Textual Features","paper_date":"2022-08-19","code_links":[],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51428,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"ML-Decoder(TResNet-XL, resolution 640)","metrics":{"mAP":"91.4"},"paper_url":"https://arxiv.org/abs/2111.12933v2","paper_title":"ML-Decoder: Scalable and Versatile Classification Head","paper_date":"2021-11-25","code_links":[{"title":"alibaba-miil/ml_decoder","url":"https://github.com/alibaba-miil/ml_decoder"}],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51429,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"Q2L-CvT(ImageNet-21K pretraining, resolution 384)","metrics":{"mAP":"91.3"},"paper_url":"https://arxiv.org/abs/2107.10834v1","paper_title":"Query2Label: A Simple Transformer Way to Multi-Label Classification","paper_date":"2021-07-22","code_links":[{"title":"SlongLiu/query2labels","url":"https://github.com/SlongLiu/query2labels"},{"title":"curt-tigges/query2label","url":"https://github.com/curt-tigges/query2label"},{"title":"averyfallson/rmffn","url":"https://github.com/averyfallson/rmffn"}],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51430,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"MLD-TResNet-L-AAM[640x640]","metrics":{"mAP":"91.30"},"paper_url":"https://arxiv.org/abs/2209.06585v2","paper_title":"Combining Metric Learning and Attention Heads For Accurate and Efficient Multilabel Image Classification","paper_date":"2022-09-14","code_links":[{"title":"openvinotoolkit/deep-object-reid","url":"https://github.com/openvinotoolkit/deep-object-reid"}],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51431,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"ML-Decoder(TResNet-L, resolution 640)","metrics":{"mAP":"91.1"},"paper_url":"https://arxiv.org/abs/2111.12933v2","paper_title":"ML-Decoder: Scalable and Versatile Classification Head","paper_date":"2021-11-25","code_links":[{"title":"alibaba-miil/ml_decoder","url":"https://github.com/alibaba-miil/ml_decoder"}],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51432,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"Q2L-SwinL(ImageNet-21K pretraining, resolution 384)","metrics":{"mAP":"90.5"},"paper_url":"https://arxiv.org/abs/2107.10834v1","paper_title":"Query2Label: A Simple Transformer Way to Multi-Label Classification","paper_date":"2021-07-22","code_links":[{"title":"SlongLiu/query2labels","url":"https://github.com/SlongLiu/query2labels"},{"title":"curt-tigges/query2label","url":"https://github.com/curt-tigges/query2label"},{"title":"averyfallson/rmffn","url":"https://github.com/averyfallson/rmffn"}],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51433,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"Q2L-TResL(ImageNet-21K pretraining, resolution 640)","metrics":{"mAP":"90.3"},"paper_url":"https://arxiv.org/abs/2107.10834v1","paper_title":"Query2Label: A Simple Transformer Way to Multi-Label Classification","paper_date":"2021-07-22","code_links":[{"title":"SlongLiu/query2labels","url":"https://github.com/SlongLiu/query2labels"},{"title":"curt-tigges/query2label","url":"https://github.com/curt-tigges/query2label"},{"title":"averyfallson/rmffn","url":"https://github.com/averyfallson/rmffn"}],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51434,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"IDA-SwinL","metrics":{"mAP":"90.3"},"paper_url":"https://openreview.net/forum?id=8XqDnrmZQNF","paper_title":"Causality Compensated Attention for Contextual Biased Visual Recognition","paper_date":"2023-02-25","code_links":[{"title":"yu-gi-oh-leilei/IDA_2023ICLR","url":"https://github.com/yu-gi-oh-leilei/IDA_2023ICLR"}],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51435,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"CCD-SwinL","metrics":{"mAP":"90.3"},"paper_url":"http://openaccess.thecvf.com//content/CVPR2022/html/Liu_Contextual_Debiasing_for_Visual_Recognition_With_Causal_Mechanisms_CVPR_2022_paper.html","paper_title":"Contextual Debiasing for Visual Recognition With Causal Mechanisms","paper_date":"2022-01-01","code_links":[{"title":"farewellthree/Causal-Context-Debiasing","url":"https://github.com/farewellthree/Causal-Context-Debiasing"}],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51436,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"MlTr-XL(ImageNet-21K pretraining, resolution 384)","metrics":{"mAP":"90.0"},"paper_url":"https://arxiv.org/abs/2106.06195v1","paper_title":"MlTr: Multi-label Classification with Transformer","paper_date":"2021-06-11","code_links":[{"title":"starmemda/MlTr","url":"https://github.com/starmemda/MlTr"}],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51437,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"TResNet-L-V2, (ImageNet-21K-P pretraining, resolution 640)","metrics":{"mAP":"89.8"},"paper_url":"https://arxiv.org/abs/2104.10972v4","paper_title":"ImageNet-21K Pretraining for the Masses","paper_date":"2021-04-22","code_links":[{"title":"Alibaba-MIIL/ImageNet21K","url":"https://github.com/Alibaba-MIIL/ImageNet21K"},{"title":"YutingLi0606/SURE","url":"https://github.com/YutingLi0606/SURE"},{"title":"encounter1997/fp-detr","url":"https://github.com/encounter1997/fp-detr"},{"title":"gregorbachmann/scaling_mlps","url":"https://github.com/gregorbachmann/scaling_mlps"},{"title":"MS-Mind/MS-Code-01","url":"https://github.com/MS-Mind/MS-Code-01/tree/main/mass"}],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51438,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"MlTr-L(ImageNet-21K pretraining, resolution 384)","metrics":{"mAP":"88.5"},"paper_url":"https://arxiv.org/abs/2106.06195v1","paper_title":"MlTr: Multi-label Classification with Transformer","paper_date":"2021-06-11","code_links":[{"title":"starmemda/MlTr","url":"https://github.com/starmemda/MlTr"}],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51439,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"TResNet-XL (resolution 640)","metrics":{"mAP":"88.4"},"paper_url":"https://arxiv.org/abs/2009.14119v4","paper_title":"Asymmetric Loss For Multi-Label Classification","paper_date":"2020-09-29","code_links":[{"title":"Alibaba-MIIL/ASL","url":"https://github.com/Alibaba-MIIL/ASL"},{"title":"mrT23/TResNet","url":"https://github.com/mrT23/TResNet"},{"title":"Alibaba-MIIL/TResNet","url":"https://github.com/Alibaba-MIIL/TResNet"},{"title":"kalelpark/ral","url":"https://github.com/kalelpark/ral"},{"title":"SlongLiu/ASL_reproduce","url":"https://github.com/SlongLiu/ASL_reproduce"}],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51440,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"TResNet-L-V2, (ImageNet-21K-P pretraining, resolution 448)","metrics":{"mAP":"88.4"},"paper_url":"https://arxiv.org/abs/2104.10972v4","paper_title":"ImageNet-21K Pretraining for the Masses","paper_date":"2021-04-22","code_links":[{"title":"Alibaba-MIIL/ImageNet21K","url":"https://github.com/Alibaba-MIIL/ImageNet21K"},{"title":"YutingLi0606/SURE","url":"https://github.com/YutingLi0606/SURE"},{"title":"encounter1997/fp-detr","url":"https://github.com/encounter1997/fp-detr"},{"title":"gregorbachmann/scaling_mlps","url":"https://github.com/gregorbachmann/scaling_mlps"},{"title":"MS-Mind/MS-Code-01","url":"https://github.com/MS-Mind/MS-Code-01/tree/main/mass"}],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51441,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"GKGNet(resolution 576)","metrics":{"mAP":"87.7"},"paper_url":"https://arxiv.org/abs/2308.14378v3","paper_title":"GKGNet: Group K-Nearest Neighbor based Graph Convolutional Network for Multi-Label Image Recognition","paper_date":"2023-08-28","code_links":[{"title":"jin-s13/gkgnet","url":"https://github.com/jin-s13/gkgnet"}],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51442,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"M3TR(ImageNet-21K-P pretraining, resolution 448)","metrics":{"mAP":"87.5"},"paper_url":"https://dl.acm.org/doi/10.1145/3474085.3475191","paper_title":"M3TR: Multi-modal Multi-label Recognition with Transformer","paper_date":"2021-10-01","code_links":[{"title":"iCVTEAM/M3TR","url":"https://github.com/iCVTEAM/M3TR"}],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51443,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"GKGNet(resolution 448)","metrics":{"mAP":"86.7"},"paper_url":"https://arxiv.org/abs/2308.14378v3","paper_title":"GKGNet: Group K-Nearest Neighbor based Graph Convolutional Network for Multi-Label Image Recognition","paper_date":"2023-08-28","code_links":[{"title":"jin-s13/gkgnet","url":"https://github.com/jin-s13/gkgnet"}],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51444,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"TResNet-L (resolution 448)","metrics":{"mAP":"86.6"},"paper_url":"https://arxiv.org/abs/2009.14119v4","paper_title":"Asymmetric Loss For Multi-Label Classification","paper_date":"2020-09-29","code_links":[{"title":"Alibaba-MIIL/ASL","url":"https://github.com/Alibaba-MIIL/ASL"},{"title":"mrT23/TResNet","url":"https://github.com/mrT23/TResNet"},{"title":"Alibaba-MIIL/TResNet","url":"https://github.com/Alibaba-MIIL/TResNet"},{"title":"kalelpark/ral","url":"https://github.com/kalelpark/ral"},{"title":"SlongLiu/ASL_reproduce","url":"https://github.com/SlongLiu/ASL_reproduce"}],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51445,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"IDA-R101","metrics":{"mAP":"86.3"},"paper_url":"https://openreview.net/forum?id=8XqDnrmZQNF","paper_title":"Causality Compensated Attention for Contextual Biased Visual Recognition","paper_date":"2023-02-25","code_links":[{"title":"yu-gi-oh-leilei/IDA_2023ICLR","url":"https://github.com/yu-gi-oh-leilei/IDA_2023ICLR"}],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51446,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"TDRG-R101(576×576)","metrics":{"mAP":"86.0"},"paper_url":"https://arxiv.org/abs/2110.04722v2","paper_title":"Transformer-based Dual Relation Graph for Multi-label Image Recognition","paper_date":"2021-10-10","code_links":[{"title":"iCVTEAM/TDRG","url":"https://github.com/iCVTEAM/TDRG"}],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51447,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"CCD-R101","metrics":{"mAP":"85.3"},"paper_url":"http://openaccess.thecvf.com//content/CVPR2022/html/Liu_Contextual_Debiasing_for_Visual_Recognition_With_Causal_Mechanisms_CVPR_2022_paper.html","paper_title":"Contextual Debiasing for Visual Recognition With Causal Mechanisms","paper_date":"2022-01-01","code_links":[{"title":"farewellthree/Causal-Context-Debiasing","url":"https://github.com/farewellthree/Causal-Context-Debiasing"}],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51448,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"ADD-GCN","metrics":{"mAP":"85.2"},"paper_url":"https://arxiv.org/abs/2012.02994v1","paper_title":"Attention-Driven Dynamic Graph Convolutional Network for Multi-Label Image Recognition","paper_date":"2020-12-05","code_links":[{"title":"Yejin0111/ADD-GCN","url":"https://github.com/Yejin0111/ADD-GCN"}],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51449,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"Q2L-R101(resolution 448)","metrics":{"mAP":"84.9"},"paper_url":"https://arxiv.org/abs/2107.10834v1","paper_title":"Query2Label: A Simple Transformer Way to Multi-Label Classification","paper_date":"2021-07-22","code_links":[{"title":"SlongLiu/query2labels","url":"https://github.com/SlongLiu/query2labels"},{"title":"curt-tigges/query2label","url":"https://github.com/curt-tigges/query2label"},{"title":"averyfallson/rmffn","url":"https://github.com/averyfallson/rmffn"}],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51450,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"TDRG-R101(448×448)","metrics":{"mAP":"84.6"},"paper_url":"https://arxiv.org/abs/2110.04722v2","paper_title":"Transformer-based Dual Relation Graph for Multi-label Image Recognition","paper_date":"2021-10-10","code_links":[{"title":"iCVTEAM/TDRG","url":"https://github.com/iCVTEAM/TDRG"}],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51451,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"MCAR (ResNet101, 576x576)","metrics":{"mAP":"84.5"},"paper_url":"https://arxiv.org/abs/2007.01755v3","paper_title":"Learning to Discover Multi-Class Attentional Regions for Multi-Label Image Recognition","paper_date":"2020-07-03","code_links":[{"title":"gaobb/MCAR","url":"https://github.com/gaobb/MCAR"}],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51452,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"MS-CMA","metrics":{"mAP":"83.8"},"paper_url":"https://arxiv.org/abs/1912.07872v2","paper_title":"Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification","paper_date":"2019-12-17","code_links":[],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51453,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"MCAR (ResNet101, 448x448)","metrics":{"mAP":"83.8"},"paper_url":"https://arxiv.org/abs/2007.01755v3","paper_title":"Learning to Discover Multi-Class Attentional Regions for Multi-Label Image Recognition","paper_date":"2020-07-03","code_links":[{"title":"gaobb/MCAR","url":"https://github.com/gaobb/MCAR"}],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51454,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"KSSNet","metrics":{"mAP":"83.7"},"paper_url":"https://arxiv.org/abs/1911.09243v1","paper_title":"Multi-Label Classification with Label Graph Superimposing","paper_date":"2019-11-21","code_links":[{"title":"Alibaba-MIIL/TResNet","url":"https://github.com/Alibaba-MIIL/TResNet"},{"title":"mathkey/mssnet","url":"https://github.com/mathkey/mssnet"},{"title":"meowbutlerdev/KSSNet","url":"https://github.com/meowbutlerdev/KSSNet"}],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51455,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"MSRN","metrics":{"mAP":"83.4"},"paper_url":"https://arxiv.org/abs/2106.11596v1","paper_title":"Multi-layered Semantic Representation Network for Multi-label Image Classification","paper_date":"2021-06-22","code_links":[{"title":"chehao2628/MSRN","url":"https://github.com/chehao2628/MSRN"}],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51456,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"ML-GCN","metrics":{"mAP":"83.0"},"paper_url":"https://arxiv.org/abs/1912.11757v1","paper_title":"Multi-Label Graph Convolutional Network Representation Learning","paper_date":"2019-12-26","code_links":[],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51457,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"GKGNet(resolution 224)","metrics":{"mAP":"82"},"paper_url":"https://arxiv.org/abs/2308.14378v3","paper_title":"GKGNet: Group K-Nearest Neighbor based Graph Convolutional Network for Multi-Label Image Recognition","paper_date":"2023-08-28","code_links":[{"title":"jin-s13/gkgnet","url":"https://github.com/jin-s13/gkgnet"}],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":51458,"task":"Multi-Label Classification","parent_task":null,"dataset":"MS-COCO","model_name":"ResNet-SRN","metrics":{"mAP":"77.1"},"paper_url":"http://arxiv.org/abs/1702.05891v2","paper_title":"Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification","paper_date":"2017-02-20","code_links":[{"title":"zhufengx/SRN_multilabel","url":"https://github.com/zhufengx/SRN_multilabel"},{"title":"Enjia/Spatial-Regularization-Network-in-Tensorflow","url":"https://github.com/Enjia/Spatial-Regularization-Network-in-Tensorflow"}],"metrics_order":"[\"mAP\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]}]}