paper-with-me

Multi-Label Classification 벤치마크

Multi-Label Classification on MS-COCO

35개 결과 · ⬇ CSV · JSON

mAP

77.1 82.47 87.85 93.22 98.6 2017-02 2026-09 ResNet-SRN — 77.1 (2017-02-20) KSSNet — 83.7 (2019-11-21) MS-CMA — 83.8 (2019-12-17) ML-GCN — 83.0 (2019-12-26) MCAR (ResNet101, 576x576) — 84.5 (2020-07-03) MCAR (ResNet101, 448x448) — 83.8 (2020-07-03) TResNet-XL (resolution 640) — 88.4 (2020-09-29) TResNet-L (resolution 448) — 86.6 (2020-09-29) ADD-GCN — 85.2 (2020-12-05) TResNet-L-V2, (ImageNet-21K-P pretraining, resolution 640) — 89.8 (2021-04-22) TResNet-L-V2, (ImageNet-21K-P pretraining, resolution 448) — 88.4 (2021-04-22) MlTr-XL(ImageNet-21K pretraining, resolution 384) — 90.0 (2021-06-11) MlTr-L(ImageNet-21K pretraining, resolution 384) — 88.5 (2021-06-11) MSRN — 83.4 (2021-06-22) Q2L-CvT(ImageNet-21K pretraining, resolution 384) — 91.3 (2021-07-22) Q2L-SwinL(ImageNet-21K pretraining, resolution 384) — 90.5 (2021-07-22) Q2L-TResL(ImageNet-21K pretraining, resolution 640) — 90.3 (2021-07-22) Q2L-R101(resolution 448) — 84.9 (2021-07-22) M3TR(ImageNet-21K-P pretraining, resolution 448) — 87.5 (2021-10-01) TDRG-R101(576×576) — 86.0 (2021-10-10) TDRG-R101(448×448) — 84.6 (2021-10-10) ML-Decoder(TResNet-XL, resolution 640) — 91.4 (2021-11-25) ML-Decoder(TResNet-L, resolution 640) — 91.1 (2021-11-25) CCD-SwinL — 90.3 (2022-01-01) CCD-R101 — 85.3 (2022-01-01) ADDS(ViT-L-336, resolution 1344) — 93.54 (2022-08-19) ADDS(ViT-L-336, resolution 640) — 93.41 (2022-08-19) ADDS(ViT-L-336, resolution 336) — 91.76 (2022-08-19) MLD-TResNet-L-AAM[640x640] — 91.3 (2022-09-14) IDA-SwinL — 90.3 (2023-02-25) IDA-R101 — 86.3 (2023-02-25) GKGNet(resolution 576) — 87.7 (2023-08-28) GKGNet(resolution 448) — 86.7 (2023-08-28) GKGNet(resolution 224) — 82.0 (2023-08-28) Diffusion-Based Cross-Modal Feature Extr — 98.6 (2025-09-19) ResNet-SRN — 77.1 (2017-02-20) KSSNet — 83.7 (2019-11-21) MS-CMA — 83.8 (2019-12-17) MCAR (ResNet101, 576x576) — 84.5 (2020-07-03) TResNet-XL (resolution 640) — 88.4 (2020-09-29) TResNet-L-V2, (ImageNet-21K-P pretraining, resolution 640) — 89.8 (2021-04-22) MlTr-XL(ImageNet-21K pretraining, resolution 384) — 90.0 (2021-06-11) Q2L-CvT(ImageNet-21K pretraining, resolution 384) — 91.3 (2021-07-22) ML-Decoder(TResNet-XL, resolution 640) — 91.4 (2021-11-25) ADDS(ViT-L-336, resolution 1344) — 93.54 (2022-08-19) Diffusion-Based Cross-Modal Feature Extr — 98.6 (2025-09-19)
RankModel mAP PaperCodeYear
1 Diffusion-Based Cross-Modal Feature Extr 자동 추출 98.6 Diffusion-Based Cross-Modal Feature Extraction for Multi-Label Classification 2025
2 ADDS(ViT-L-336, resolution 1344) 93.54 Open Vocabulary Multi-Label Classification with Dual-Modal Decoder on Aligned Visual-Textual Features 2022
3 ADDS(ViT-L-336, resolution 640) 93.41 Open Vocabulary Multi-Label Classification with Dual-Modal Decoder on Aligned Visual-Textual Features 2022
4 ADDS(ViT-L-336, resolution 336) 91.76 Open Vocabulary Multi-Label Classification with Dual-Modal Decoder on Aligned Visual-Textual Features 2022
5 ML-Decoder(TResNet-XL, resolution 640) 91.4 ML-Decoder: Scalable and Versatile Classification Head alibaba-miil/ml_decoder 2021
6 Q2L-CvT(ImageNet-21K pretraining, resolution 384) 91.3 Query2Label: A Simple Transformer Way to Multi-Label Classification SlongLiu/query2labels · curt-tigges/query2label · averyfallson/rmffn 2021
6 MLD-TResNet-L-AAM[640x640] 91.30 Combining Metric Learning and Attention Heads For Accurate and Efficient Multilabel Image Classification openvinotoolkit/deep-object-reid 2022
8 ML-Decoder(TResNet-L, resolution 640) 91.1 ML-Decoder: Scalable and Versatile Classification Head alibaba-miil/ml_decoder 2021
9 Q2L-SwinL(ImageNet-21K pretraining, resolution 384) 90.5 Query2Label: A Simple Transformer Way to Multi-Label Classification SlongLiu/query2labels · curt-tigges/query2label · averyfallson/rmffn 2021
10 Q2L-TResL(ImageNet-21K pretraining, resolution 640) 90.3 Query2Label: A Simple Transformer Way to Multi-Label Classification SlongLiu/query2labels · curt-tigges/query2label · averyfallson/rmffn 2021
10 IDA-SwinL 90.3 Causality Compensated Attention for Contextual Biased Visual Recognition yu-gi-oh-leilei/IDA_2023ICLR 2023
10 CCD-SwinL 90.3 Contextual Debiasing for Visual Recognition With Causal Mechanisms farewellthree/Causal-Context-Debiasing 2022
13 MlTr-XL(ImageNet-21K pretraining, resolution 384) 90.0 MlTr: Multi-label Classification with Transformer starmemda/MlTr 2021
14 TResNet-L-V2, (ImageNet-21K-P pretraining, resolution 640) 89.8 ImageNet-21K Pretraining for the Masses Alibaba-MIIL/ImageNet21K · YutingLi0606/SURE · encounter1997/fp-detr · +2 2021
15 MlTr-L(ImageNet-21K pretraining, resolution 384) 88.5 MlTr: Multi-label Classification with Transformer starmemda/MlTr 2021
16 TResNet-XL (resolution 640) 88.4 Asymmetric Loss For Multi-Label Classification Alibaba-MIIL/ASL · mrT23/TResNet · Alibaba-MIIL/TResNet · +2 2020
16 TResNet-L-V2, (ImageNet-21K-P pretraining, resolution 448) 88.4 ImageNet-21K Pretraining for the Masses Alibaba-MIIL/ImageNet21K · YutingLi0606/SURE · encounter1997/fp-detr · +2 2021
18 GKGNet(resolution 576) 87.7 GKGNet: Group K-Nearest Neighbor based Graph Convolutional Network for Multi-Label Image Recognition jin-s13/gkgnet 2023
19 M3TR(ImageNet-21K-P pretraining, resolution 448) 87.5 M3TR: Multi-modal Multi-label Recognition with Transformer iCVTEAM/M3TR 2021
20 GKGNet(resolution 448) 86.7 GKGNet: Group K-Nearest Neighbor based Graph Convolutional Network for Multi-Label Image Recognition jin-s13/gkgnet 2023
1–20 / 35 다음 → 페이지당 10 20 50 100