Multi-label Classification on VOC 2007
95.2mAP (Average)TRM-ML
Evaluation Results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| TRM-MLVenue=ACM MM′24, Backbone=clip2025.10 | 95.2 | 93.9 | 94.6 | 94.9 | 95.3 | 95.4 | 95.6 | 95.6 | 95.6 | 95.7 | |
| T2I-PALVenue=TPAMI′25, Backbone=clip2025.10 | 95 | 93.7 | 94.8 | 94.8 | 94.9 | 94.9 | 95.2 | 95.5 | 95.5 | 95.5 | |
| CSL*Venue=Ours, Backbone=clip2025.10 | 95 | 91.7 | 93.7 | 94.6 | 95.1 | 95.6 | 95.7 | 96.1 | 96.3 | 96.3 | |
| TaI-DPTVenue=CVPR′23, Backbone=clip2025.10 | 94.8 | 93.3 | 94.6 | 94.8 | 94.9 | 95.1 | 95 | 95.1 | 95.3 | 95.5 | |
| DualCoOp++Venue=TPAMI’23, Backbone=clip2025.10 | 94.1 | 92.7 | 93.4 | 93.8 | 94 | 94.3 | 94.4 | 94.4 | 94.7 | 94.9 | |
| CSLVenue=Ours, Backbone=vanilla2025.10 | 93.8 | 89.9 | 92.4 | 93.5 | 94 | 94.4 | 94.6 | 94.8 | 95.2 | 95.2 | |
| PU-MLC*Venue=ICME′24, Backbone=clip2025.10 | 93.7 | 91.3 | 92.9 | 93.3 | 93.7 | 93.8 | 94.3 | 94.5 | 94.6 | 94.8 | |
| SCPNetVenue=CVPR′23, Backbone=clip2025.10 | 93.5 | 91.1 | 92.8 | 93.5 | 93.6 | 93.8 | 94 | 94.1 | 94.2 | 94.3 | |
| DualCoOpVenue=NeurIPS′22, Backbone=clip2025.10 | 93.2 | 90.3 | 92.2 | 92.8 | 93.3 | 93.6 | 93.9 | 94 | 94.1 | 94.2 | |
| D2ACEArchitecture=HST2026.05 | 93.2 | — | — | — | — | — | — | — | — | — | |
| ML-UncArchitecture=HST2026.05 | 93.14 | — | — | — | — | — | — | — | — | — | |
| D2ACEArchitecture=ML-GCN2026.05 | 93.14 | — | — | — | — | — | — | — | — | — | |
| DIHCLArchitecture=HST2026.05 | 93.1 | — | — | — | — | — | — | — | — | — | |
| RecentArchitecture=HST2026.05 | 93.08 | — | — | — | — | — | — | — | — | — | |
| DIHCLArchitecture=ML-GCN2026.05 | 93.08 | — | — | — | — | — | — | — | — | — | |
| ML-UncArchitecture=ML-GCN2026.05 | 93.05 | — | — | — | — | — | — | — | — | — | |
| RandomArchitecture=HST2026.05 | 93 | — | — | — | — | — | — | — | — | — | |
| Hard-ImbArchitecture=HST2026.05 | 93 | — | — | — | — | — | — | — | — | — | |
| BalanceArchitecture=HST2026.05 | 92.98 | — | — | — | — | — | — | — | — | — | |
| Hard-ImbArchitecture=ML-GCN2026.05 | 92.98 | — | — | — | — | — | — | — | — | — | |
| RecentArchitecture=ML-GCN2026.05 | 92.95 | — | — | — | — | — | — | — | — | — | |
| ActiveArchitecture=HST2026.05 | 92.94 | — | — | — | — | — | — | — | — | — | |
| RandomArchitecture=ML-GCN2026.05 | 92.93 | — | — | — | — | — | — | — | — | — | |
| BalanceArchitecture=ML-GCN2026.05 | 92.89 | — | — | — | — | — | — | — | — | — | |
| ActiveArchitecture=ML-GCN2026.05 | 92.85 | — | — | — | — | — | — | — | — | — | |
| TagCLIPSupervision=Unsupervised, Label=None, Backbone=ResNet-1012026.06 | 92.8 | — | — | — | — | — | — | — | — | — | |
| TailorCLIPSupervision=Unsupervised, Label=None, Backbone=ViT-L/142026.06 | 92.8 | — | — | — | — | — | — | — | — | — | |
| BCE-LSSupervision=Fully Supervised, Label=Full, Backbone=ResNet-1012026.06 | 92.6 | — | — | — | — | — | — | — | — | — | |
| PU-MLCVenue=ICME′24, Backbone=vanilla2025.10 | 92 | 88 | 90.7 | 91.9 | 92 | 92.4 | 92.7 | 93 | 93.4 | 93.5 | |
| TailorCLIPSupervision=Unsupervised, Label=None, Backbone=ResNet-1012026.06 | 91.8 | — | — | — | — | — | — | — | — | — | |
| BCESupervision=Fully Supervised, Label=Full, Backbone=ResNet-1012026.06 | 91.3 | — | — | — | — | — | — | — | — | — | |
| CCDSupervision=Unsupervised, Label=None, Backbone=ResNet-1012026.06 | 91 | — | — | — | — | — | — | — | — | — | |
| SARBVenue=AAAI′22, Backbone=vanilla2025.10 | 90.7 | 83.5 | 88.6 | 90.7 | 91.4 | 91.9 | 92.2 | 92.6 | 92.8 | 92.9 | |
| LL-RSupervision=Weakly Supervised, Label=One, Backbone=ResNet-1012026.06 | 90.6 | — | — | — | — | — | — | — | — | — | |
| ASLVenue=ICCV′21, Backbone=vanilla2025.10 | 90.5 | 82.9 | 88.6 | 90 | 91.2 | 91.7 | 92.2 | 92.4 | 92.5 | 92.6 | |
| SSTVenue=AAAI′22, Backbone=vanilla2025.10 | 90.4 | 81.5 | 89 | 90.3 | 91 | 91.6 | 92 | 92.5 | 92.6 | 92.7 | |
| DualCoOpSupervision=Weakly Supervised, Label=10%, Backbone=ResNet-1012026.06 | 90.3 | — | — | — | — | — | — | — | — | — | |
| Partial BCEVenue=CVPR′19, Backbone=vanilla2025.10 | 90 | 80.7 | 88.4 | 89.9 | 90.7 | 91.2 | 91.8 | 92.3 | 92.4 | 92.5 | |
| G2NetPLSupervision=Weakly Supervised, Label=One, Backbone=ResNet-1012026.06 | 89.9 | — | — | — | — | — | — | — | — | — | |
| ScobSupervision=Weakly Supervised, Label=One, Backbone=ResNet-1012026.06 | 89.7 | — | — | — | — | — | — | — | — | — | |
| SSGRLVenue=ICCV′19, Backbone=vanilla2025.10 | 89.5 | 77.7 | 87.6 | 89.9 | 90.7 | 91.4 | 91.8 | 91.9 | 92.2 | 92.2 | |
| P-GCNVenue=TPAMI′21, Backbone=vanilla2025.10 | 89.5 | 83.1 | 85.9 | 87.9 | 89.2 | 90.1 | 91.3 | 92 | 92.7 | 93 | |
| CoMCFT-FREE=false, EKE-FREE=false, OTTA=false, Backbone=ResNet-502026.06 | 89.4 | — | — | — | — | — | — | — | — | — | |
| CDULSupervision=Unsupervised, Label=None, Backbone=ResNet-1012026.06 | 89 | — | — | — | — | — | — | — | — | — | |
| SPARCFT-FREE=true, EKE-FREE=false, OTTA=false, Backbone=ViT-B/162026.06 | 88.7 | — | — | — | — | — | — | — | — | — | |
| BCPFT-FREE=true, EKE-FREE=true, OTTA=true, Backbone=ViT-B/162026.06 | 88.41 | — | — | — | — | — | — | — | — | — | |
| BCPFT-FREE=true, EKE-FREE=true, OTTA=true, Backbone=ResNet-502026.06 | 86.93 | — | — | — | — | — | — | — | — | — | |
| SARBSupervision=Weakly Supervised, Label=10%, Backbone=ResNet-1012026.06 | 85.7 | — | — | — | — | — | — | — | — | — | |
| ROLESupervision=Weakly Supervised, Label=One, Backbone=ResNet-1012026.06 | 84.6 | — | — | — | — | — | — | — | — | — | |
| Partial BCESupervision=Weakly Supervised, Label=10%, Backbone=ResNet-1012026.06 | 83.1 | — | — | — | — | — | — | — | — | — | |
| ASLSupervision=Weakly Supervised, Label=10%, Backbone=ResNet-1012026.06 | 82.9 | — | — | — | — | — | — | — | — | — | |
| SSTSupervision=Weakly Supervised, Label=10%, Backbone=ResNet-1012026.06 | 81.5 | — | — | — | — | — | — | — | — | — |