Few-shot Object Detection on CD-FSOD
281ArTaxOr ScoreETS
Evaluation Results
| Method | Links | ||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ETSSetting=Open-Source, Backbone=Swin-B2025.04 | 281 | 575 | 127 | 407 | 117 | 212 | 286.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GroundingDINO*Setting=Open-Source, Backbone=Swin-B2025.04 | 221 | 561 | 117 | 375 | 109 | 192 | 262.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CD-VitoSetting=Close-Source, Backbone=ViT-L2025.04 | 210 | 177 | 178 | 203 | 36 | 31 | 139 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DE-ViTSetting=Close-Source, Backbone=ViT-L2025.04 | 105 | 130 | 147 | 193 | 6 | 24 | 101 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| HED (Ours)Backbone=Swin-B, Shot=102026.03 | 79.2 | 59.6 | 41.5 | 46.3 | 28.4 | 32.3 | 47.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| HED (Ours)Backbone=Swin-B, Shot=52026.03 | 76.8 | 59.4 | 35.3 | 45.5 | 25.2 | 27.5 | 45 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LMPShots=10-shot, Backbone=Swin-B2026.02 | 75.1 | 62.6 | 40.4 | 44.4 | 25.7 | 31.6 | 46.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LMPShots=5-shot, Backbone=Swin-B2026.02 | 75 | 60.1 | 31.3 | 43.9 | 25.1 | 28.3 | 44 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Domain-RAGShots=10-shot, Backbone=Swin-B2026.02 | 73.4 | 61.1 | 39 | 41.3 | 26.3 | 31.2 | 45.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Domain-RAGBackbone=Swin-B, Shot=102026.03 | 73.4 | 61.1 | 39 | 41.3 | 26.3 | 31.2 | 45.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GroundingDINOShots=10-shot, Backbone=Swin-B2026.02 | 73 | 58.6 | 37.2 | 38.5 | 25.5 | 30.3 | 43.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VFMDETRBackbone=DINOv2-L, Shot=102026.03 | 71.3 | 49.9 | 37.8 | 34.1 | 23.7 | 22.1 | 39.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ETSBackbone=Swin-B, Shot=102026.03 | 71.2 | 61.5 | 37.5 | 44.1 | 26.1 | 29.8 | 45 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ETSShots=10-shot, Backbone=Swin-B2026.02 | 70.6 | 60.8 | 37.5 | 42.8 | 26.1 | 28.3 | 44.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Domain-RAGShots=5-shot, Backbone=Swin-B2026.02 | 70 | 59.8 | 31.5 | 43.8 | 24.2 | 26.8 | 42.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Domain-RAGBackbone=Swin-B, Shot=52026.03 | 70 | 59.8 | 31.5 | 43.8 | 24.2 | 26.8 | 42.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CDFormerBackbone=ViT-L/14, Shots=10, fine-tuning=true2025.05 | 68.7 | 59 | 32.5 | 35.5 | 18.1 | 26.4 | 40 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CDFormerBackbone=DINOv2-L, Shot=102026.03 | 68.7 | 59 | 32.5 | 35.5 | 18.1 | 26.4 | 40 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GroundingDINOShots=5-shot, Backbone=Swin-B2026.02 | 68.4 | 57.6 | 29.6 | 41.6 | 19.7 | 25.6 | 40.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CDFormerBackbone=ViT-L/14, Shots=5, fine-tuning=true2025.05 | 65 | 58.9 | 28.1 | 31.7 | 15 | 23.8 | 37.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CDFormerBackbone=DINOv2-L, Shot=52026.03 | 65 | 58.9 | 28.1 | 31.7 | 15 | 23.8 | 37.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ETSSetting=Open-Source, Backbone=Swin-B2025.04 | 64.5 | 60.1 | 29.3 | 44.9 | 23.5 | 28.6 | 41.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ETSShots=5-shot, Backbone=Swin-B2026.02 | 64.5 | 59.7 | 29.3 | 42.1 | 23.5 | 27.7 | 41.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ETSBackbone=Swin-B, Shot=52026.03 | 64.5 | 60.1 | 29.3 | 44.9 | 23.5 | 28.6 | 41.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VFMDETRBackbone=DINOv2-L, Shot=52026.03 | 63.3 | 45.1 | 32.1 | 29.5 | 19 | 19.6 | 34.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GroundingDINO*Setting=Open-Source, Backbone=Swin-B2025.04 | 61.9 | 59.1 | 27.7 | 43.2 | 22.2 | 27.9 | 40.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CD-VITOShots=10-shot, Fine-tuning on novel classes=true2025.07 | 60.5 | 44.3 | 30.8 | 22.3 | 12.8 | 7 | 29.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CD-ViTOBackbone=ViT-L/14, Shots=102024.02 | 60.5 | 44.3 | 30.8 | 22.3 | 12.8 | 7 | 29.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CD-VITOBackbone=ViT-L/14, Shots=102025.05 | 60.5 | 44.3 | 30.8 | 22.3 | 12.8 | 7 | 29.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CD-ViTOShots=10-shot, Backbone=ViT-L/142026.02 | 60.5 | 44.3 | 30.8 | 22.3 | 12.8 | 7 | 29.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CD-ViTOBackbone=DINOv2-L, Shot=102026.03 | 60.5 | 44.3 | 30.8 | 22.3 | 12.8 | 7 | 29.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LMPShots=1-shot, Backbone=Swin-B2026.02 | 58.5 | 58.6 | 17.2 | 36.6 | 13.3 | 21.6 | 34.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Domain-RAGShots=1-shot, Backbone=Swin-B2026.02 | 57.2 | 56.1 | 18 | 38 | 12.1 | 20.2 | 33.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Domain-RAGBackbone=Swin-B, Shot=12026.03 | 57.2 | 56.1 | 18 | 38 | 12.1 | 20.2 | 33.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| OursBackbone=Swin-T, Venue=-, Shots=52026.03 | 54.98 | 44.83 | 29.41 | 33.87 | 23.64 | 15.66 | 33.73 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DE-VIT-FT+Shots=10-shot, Fine-tuning on novel classes=true2025.07 | 49.2 | 40.8 | 25.6 | 21.3 | 8.8 | 5.4 | 25.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DE-VIT-FT+Backbone=ViT-L/14, Shots=102024.02 | 49.2 | 40.8 | 25.6 | 21.3 | 8.8 | 5.4 | 25.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DE-VIT-FTBackbone=ViT-L/14, Shots=10, fine-tuning=true2025.05 | 49.2 | 40.8 | 25.6 | 21.3 | 8.8 | 5.4 | 25.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DE-ViT-FT†Backbone=DINOv2-L, Shot=102026.03 | 49.2 | 40.8 | 25.6 | 21.3 | 8.8 | 5.4 | 25.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GLIPBackbone=Swin-T, Venue=CVPR’22, Shots=52026.03 | 49.11 | 39.28 | 28.39 | 28.4 | 19.55 | 11.4 | 29.36 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| HED (Ours)Backbone=Swin-B, Shot=12026.03 | 49.1 | 55.6 | 24.6 | 42.7 | 15.5 | 22.1 | 34.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VFM-MoE*Backbone=Swin-T, Venue=NIPS’25, Shots=52026.03 | 48.23 | 39.13 | 26.34 | 27.58 | 18.67 | 10.73 | 28.45 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CD-ViTO*Backbone=Swin-T, Venue=ECCV’24, Shots=52026.03 | 48.12 | 40.28 | 27.05 | 28.26 | 16.84 | 9.24 | 28.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CD-VITOShots=5-shot, Fine-tuning on novel classes=true2025.07 | 47.9 | 41.1 | 26.9 | 22.3 | 11.4 | 6.8 | 26.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CD-ViTOBackbone=ViT-L/14, Shots=52024.02 | 47.9 | 41.1 | 26.9 | 22.3 | 11.4 | 6.8 | 26.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CD-VitoSetting=Close-Source, Backbone=ViT-L2025.04 | 47.9 | 41.1 | 26.9 | 22.3 | 11.4 | 6.8 | 26.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CD-VITOBackbone=ViT-L/14, Shots=52025.05 | 47.9 | 41.1 | 26.9 | 22.3 | 11.4 | 6.8 | 26.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CD-ViTOShots=5-shot, Backbone=ViT-L/142026.02 | 47.9 | 41.1 | 26.9 | 22.3 | 11.4 | 6.8 | 26.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CD-ViTO†Backbone=ViT-L/14, Venue=ECCV’24, Shots=52026.03 | 47.9 | 41.1 | 26.9 | 22.3 | 11.4 | 6.8 | 26.07 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CD-ViTOBackbone=DINOv2-L, Shot=52026.03 | 47.9 | 41.1 | 26.9 | 22.3 | 11.4 | 6.8 | 26.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Domain-RAG*Backbone=Swin-T, Venue=NIPS’25, Shots=52026.03 | 46.13 | 41.47 | 25.23 | 27.67 | 17.53 | 9.87 | 27.98 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CDFormerBackbone=ViT-L/14, Shots=5, fine-tuning=false2025.05 | 38.4 | 53.6 | 7.9 | 24.6 | 3.6 | 16.5 | 24.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DE-ViT*Backbone=Swin-T, Venue=arXiv’23, Shots=52026.03 | 38.15 | 38.27 | 23.52 | 25.89 | 11.5 | 6.79 | 24.02 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DE-VIT-FT+Shots=5-shot, Fine-tuning on novel classes=true2025.07 | 38 | 38.1 | 23.4 | 21.2 | 7.8 | 5 | 22.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DE-VIT-FT+Backbone=ViT-L/14, Shots=52024.02 | 38 | 38.1 | 23.4 | 21.2 | 7.8 | 5 | 22.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DE-ViTSetting=Close-Source, Backbone=ViT-L2025.04 | 38 | 38.1 | 23.4 | 21.2 | 7.8 | 5 | 22.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DE-VIT-FTBackbone=ViT-L/14, Shots=5, fine-tuning=true2025.05 | 38 | 38.1 | 23.4 | 21.2 | 7.8 | 5 | 22.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DE-ViT†Backbone=ViT-L/14, Venue=arXiv’23, Shots=52026.03 | 38 | 38.1 | 23.4 | 21.2 | 7.8 | 5 | 22.25 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DE-ViT-FT†Backbone=DINOv2-L, Shot=52026.03 | 38 | 38.1 | 23.4 | 21.2 | 7.8 | 5 | 22.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CDFormerBackbone=ViT-L/14, Shots=10, fine-tuning=false2025.05 | 37.3 | 53.5 | 7.9 | 25.7 | 4 | 16.7 | 24.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CDFormerBackbone=ViT-L/14, Shots=1, fine-tuning=true2025.05 | 36 | 54 | 16.3 | 34.5 | 7.4 | 12.7 | 26.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CDFormerBackbone=DINOv2-L, Shot=12026.03 | 36 | 54 | 16.3 | 34.5 | 7.4 | 12.7 | 26.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Training-freeShots=5-shot, Fine-tuning on novel classes=false2025.07 | 35.7 | 24.9 | 18.5 | 29.6 | 5.2 | 20.2 | 22.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Training-freeShots=10-shot, Fine-tuning on novel classes=false2025.07 | 35 | 25.9 | 16.4 | 29.6 | 5.5 | 16 | 21.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DeticSetting=Close-Source, Backbone=ViT-L2025.04 | 32 | 151 | 41 | 90 | 38 | 42 | 66 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CDFormerBackbone=ViT-L/14, Shots=1, fine-tuning=false2025.05 | 29.4 | 49.6 | 8 | 27.7 | 3 | 12.2 | 21.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Training-freeShots=1-shot, Fine-tuning on novel classes=false2025.07 | 28.2 | 18.9 | 14.9 | 30.5 | 5.5 | 10 | 18 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ETSShots=1-shot, Backbone=Swin-B2026.02 | 28.1 | 55.8 | 12.7 | 39.3 | 11.7 | 18.9 | 27.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ETSBackbone=Swin-B, Shot=12026.03 | 28.1 | 57.5 | 12.7 | 40.7 | 11.7 | 21.2 | 28.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| OursBackbone=Swin-T, Venue=-, Shots=12026.03 | 27.93 | 38.75 | 25.67 | 30.43 | 12.88 | 7.18 | 23.81 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GroundingDINOShots=1-shot, Backbone=Swin-B2026.02 | 26.3 | 55.3 | 14.8 | 36.4 | 9.3 | 15.9 | 26.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VFMDETRBackbone=DINOv2-L, Shot=12026.03 | 26.1 | 20.1 | 20.6 | 24.2 | 9.1 | 9 | 18.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ViTDeT-FT+Shots=10-shot, Fine-tuning on novel classes=true2025.07 | 23.4 | 25.6 | 29.4 | 6.5 | 15.8 | 15.6 | 19.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ViTDeT-FT+Backbone=ViT-B/14, Shots=102024.02 | 23.4 | 25.6 | 29.4 | 6.5 | 15.8 | 15.6 | 19.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ViTDeT-FTBackbone=ViT-B/14, Shots=10, fine-tuning=true2025.05 | 23.4 | 25.6 | 29.4 | 6.5 | 15.8 | 15.6 | 19.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ViTDet-FTShots=10-shot, Backbone=ViT-B/142026.02 | 23.4 | 25.6 | 29.4 | 6.5 | 15.8 | 15.6 | 19.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VFM-MoE*Backbone=Swin-T, Venue=NIPS’25, Shots=12026.03 | 23.38 | 25.67 | 19.03 | 25.45 | 8.12 | 3.87 | 17.59 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Domain-RAG*Backbone=Swin-T, Venue=NIPS’25, Shots=12026.03 | 21.47 | 22.53 | 18.97 | 24.67 | 7.53 | 3.92 | 16.52 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GLIPBackbone=Swin-T, Venue=CVPR’22, Shots=12026.03 | 21.4 | 33.35 | 19.09 | 27.23 | 8.84 | 3.99 | 18.98 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ViTDet*Backbone=Swin-T, Venue=ECCV’22, Shots=52026.03 | 21.05 | 23.45 | 23.45 | 11.03 | 19.96 | 15.07 | 19 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CD-VITOShots=1-shot, Fine-tuning on novel classes=true2025.07 | 21 | 17.7 | 17.8 | 20.3 | 3.6 | 3.1 | 13.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CD-ViTOBackbone=ViT-L/14, Shots=12024.02 | 21 | 17.7 | 17.8 | 20.3 | 3.6 | 3.1 | 13.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CD-VITOBackbone=ViT-L/14, Shots=12025.05 | 21 | 17.7 | 17.8 | 20.3 | 3.6 | 3.1 | 13.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CD-ViTOShots=1-shot, Backbone=ViT-L/142026.02 | 21 | 17.7 | 17.8 | 20.3 | 3.6 | 3.1 | 13.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CD-ViTO†Backbone=ViT-L/14, Venue=ECCV’24, Shots=12026.03 | 21 | 17.7 | 17.8 | 20.3 | 3.6 | 3.1 | 13.92 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CD-ViTOBackbone=DINOv2-L, Shot=12026.03 | 21 | 17.7 | 17.8 | 20.3 | 3.6 | 3.1 | 13.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ViTDeT-FT+Shots=5-shot, Fine-tuning on novel classes=true2025.07 | 20.9 | 23.3 | 23.3 | 9 | 13.5 | 11.1 | 16.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ViTDeT-FT+Backbone=ViT-B/14, Shots=52024.02 | 20.9 | 23.3 | 23.3 | 9 | 13.5 | 11.1 | 16.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ViTDeT-FTBackbone=ViT-B/14, Shots=5, fine-tuning=true2025.05 | 20.9 | 23.3 | 23.3 | 9 | 13.5 | 11.1 | 16.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ViTDet-FTShots=5-shot, Backbone=ViT-B/142026.02 | 20.9 | 23.3 | 23.3 | 9 | 13.5 | 11.1 | 16.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ViTDet†Backbone=ViT-B/14, Venue=ECCV’22, Shots=52026.03 | 20.9 | 23.3 | 23.3 | 9 | 13.5 | 11.1 | 16.85 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CD-ViTO*Backbone=Swin-T, Venue=ECCV’24, Shots=12026.03 | 20.85 | 21.83 | 18.9 | 23.53 | 6.82 | 3.85 | 15.96 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Distill-cdfsdShots=10-shot, Fine-tuning on novel classes=true2025.07 | 18.1 | 27.3 | 26.5 | 15.5 | 21.1 | 14.5 | 20.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Distill-cdfsodBackbone=ResNet50, Shots=102024.02 | 18.1 | 27.3 | 26.5 | 15.5 | 21.1 | 14.5 | 20.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Distill-CDFSODBackbone=ResNet50, Shots=102025.05 | 18.1 | 27.3 | 26.5 | 15.5 | 21.1 | 14.5 | 20.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FSCEShots=10-shot, Fine-tuning on novel classes=true2025.07 | 15.9 | — | 21.9 | — | — | 12 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FSCEBackbone=ResNet50, Shots=102024.02 | 15.9 | — | 21.9 | — | — | 12 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FSCEBackbone=ResNet50, Shots=102025.05 | 15.9 | 21.9 | — | — | 12 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FSCEShots=10-shot, Backbone=ResNet502026.02 | 15.9 | — | 21.9 | — | — | 12 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DeFRCNShots=10-shot, Fine-tuning on novel classes=true2025.07 | 15.5 | — | 22.9 | — | — | 12.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |