Object Detection on Foggy Cityscapes 0.02 (test)
52.8AP (person)MRT
Evaluation results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| MRTDetector=Def DETR2024.03 | 52.8 | 51.7 | 68.7 | 35.9 | 58.1 | 54.5 | 41 | 47.1 | 51.2 | |
| HTDetector=FCOS2024.03 | 52.1 | 55.8 | 67.5 | 32.7 | 55.9 | 49.1 | 40.1 | 50.3 | 50.4 | |
| AQTDetector=Def DETR2024.03 | 49.3 | 52.3 | 64.4 | 27.7 | 53.7 | 46.5 | 36 | 46.4 | 47.1 | |
| OADADetector=FCOS2024.03 | 47.8 | 46.5 | 62.9 | 32.1 | 48.5 | 50.9 | 34.3 | 39.8 | 45.4 | |
| SIGMADetector=FCOS2024.03 | 46.9 | 48.4 | 63.7 | 27.1 | 50.7 | 35.9 | 34.7 | 41.4 | 43.5 | |
| CMTDetector=FRCNN2024.03 | 45.9 | 55.7 | 63.7 | 39.6 | 66 | 38.8 | 41.4 | 51.2 | 50.3 | |
| MILADetector=FRCNN2024.03 | 45.6 | 52.8 | 64.8 | 34.7 | 61.4 | 54.1 | 39.7 | 51.5 | 50.6 | |
| ATDetector=FRCNN2024.03 | 45.3 | 55.7 | 63.6 | 36.8 | 64.9 | 34.9 | 42.1 | 51.3 | 49.3 | |
| CATDetector=FRCNN2024.03 | 44.6 | 57.1 | 63.7 | 40.8 | 66 | 49.7 | 44.9 | 53 | 52.5 | |
| FACTORVisual Backbone=Swin-T, Framework=Grounding DINO, Bp-free=true2026.05 | 43.39 | 8.18 | 56.38 | 26.98 | 39.02 | 0.52 | 30.7 | 46.36 | 31.44 | |
| FACTORVisual Backbone=Swin-B, Framework=Grounding DINO, Bp-free=true2026.05 | 42.55 | 22.36 | 60.64 | 32.97 | 49.03 | 17.05 | 38.19 | 50.67 | 39.18 | |
| BCAVisual Backbone=Swin-T, Framework=Grounding DINO, Bp-free=true2026.05 | 41.01 | 5.61 | 47.85 | 21.86 | 33.4 | 0.91 | 28.47 | 29.82 | 26.12 | |
| PTDetector=FRCNN2024.03 | 40.2 | 48.8 | 59.7 | 30.7 | 51.8 | 30.6 | 35.4 | 44.5 | 42.7 | |
| TDDDetector=FRCNN2024.03 | 39.6 | 47.5 | 55.7 | 33.8 | 47.6 | 42.1 | 37 | 41.4 | 43.1 | |
| OracleDetector=FRCNN2024.03 | 39.5 | 47.3 | 59.1 | 33.1 | 47.3 | 42.9 | 38.1 | 40.8 | 43.5 | |
| BCA+Visual Backbone=Swin-T, Framework=Grounding DINO, Bp-free=true2026.05 | 39.03 | 3.61 | 46.98 | 22.26 | 35.26 | 0.87 | 29.37 | 35.87 | 26.65 | |
| TDAVisual Backbone=Swin-B, Framework=Grounding DINO, Bp-free=true2026.05 | 38.29 | 25.53 | 50.09 | 30.49 | 45.92 | 11.98 | 33.12 | 39.06 | 34.31 | |
| BCA+Visual Backbone=Swin-B, Framework=Grounding DINO, Bp-free=true2026.05 | 38.15 | 26.3 | 52.3 | 30.77 | 45.66 | 20.29 | 33.89 | 42.41 | 36.22 | |
| HisTPTVisual Backbone=Swin-B, Framework=Grounding DINO, Bp-free=false2026.05 | 37.95 | 22.46 | 54 | 29.98 | 44.11 | 12.5 | 37.27 | 42.33 | 35.07 | |
| SourceDetector=Def DETR2024.03 | 37.7 | 39.1 | 44.2 | 17.2 | 26.8 | 5.8 | 21.6 | 35.5 | 28.5 | |
| MeGADetector=FRCNN2024.03 | 37.7 | 49 | 52.4 | 25.4 | 49.2 | 46.9 | 34.5 | 39 | 41.8 | |
| SourceDetector=FCOS2024.03 | 36.9 | 36.3 | 44.1 | 18.6 | 29.3 | 8.4 | 20.3 | 31.9 | 28.2 | |
| BCAVisual Backbone=Swin-B, Framework=Grounding DINO, Bp-free=true2026.05 | 36.53 | 24.42 | 50.77 | 30.83 | 45.25 | 20.29 | 33.2 | 42.49 | 35.47 | |
| TDAVisual Backbone=Swin-T, Framework=Grounding DINO, Bp-free=true2026.05 | 35.27 | 4.87 | 46.43 | 22.82 | 32.3 | 0.38 | 28.68 | 29.86 | 25.08 | |
| GDINOVisual Backbone=Swin-B, Framework=Grounding DINO, Bp-free=true2026.05 | 34.95 | 20.35 | 51.56 | 30.01 | 45.72 | 0.87 | 35.21 | 32.06 | 31.34 | |
| TIADetector=FRCNN2024.03 | 34.8 | 46.3 | 49.7 | 31.1 | 52.1 | 48.6 | 37.7 | 38.1 | 42.3 | |
| UMTDetector=FRCNN2024.03 | 33 | 46.7 | 48.6 | 34.1 | 56.5 | 46.8 | 30.4 | 37.3 | 41.7 | |
| HisTPTVisual Backbone=Swin-T, Framework=Grounding DINO, Bp-free=false2026.05 | 32.5 | 5.09 | 47.45 | 23.13 | 34.63 | 0.85 | 28.82 | 31.98 | 25.55 | |
| GDINOVisual Backbone=Swin-T, Framework=Grounding DINO, Bp-free=true2026.05 | 30.1 | 3.42 | 46.26 | 22.41 | 31.98 | 0.08 | 27.96 | 28.87 | 23.88 | |
| STFARVisual Backbone=ResNet-50, Framework=Faster RCNN, Bp-free=false2026.05 | 28.8 | 32 | 42.4 | 15.1 | 30.1 | 11.2 | 15.5 | 26.2 | 25.1 | |
| Self-TrainingVisual Backbone=ResNet-50, Framework=Faster RCNN, Bp-free=false2026.05 | 27.7 | 30.8 | 41.4 | 12.8 | 27.4 | 4.2 | 14.8 | 26.1 | 23.1 | |
| SHOTVisual Backbone=ResNet-50, Framework=Faster RCNN, Bp-free=false2026.05 | 26.7 | 30.3 | 36.9 | 16.8 | 28.9 | 6.4 | 14.3 | 23.3 | 23 | |
| TTACVisual Backbone=ResNet-50, Framework=Faster RCNN, Bp-free=false2026.05 | 24.5 | 27.3 | 33.4 | 14.6 | 26.1 | 5.8 | 14.1 | 21.5 | 20.9 | |
| T3AVisual Backbone=ResNet-50, Framework=Faster RCNN, Bp-free=false2026.05 | 22.6 | 23 | 31.9 | 7.7 | 14.8 | 1 | 7.9 | 19.7 | 16.6 | |
| SourceDetector=FRCNN2024.03 | 22.4 | 26.6 | 28.5 | 9 | 16 | 4.3 | 15.2 | 25.3 | 18.4 |