Object Detection on Noisy Pascal VOC (NR 60%) → Clipart1k
33AP (Aero)DAF + NLTE
Evaluation results
| Method | Links | ||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DAF + NLTEBackbone=ResNet-50, Resolution=600, Noisy Rate (NR)=60%2022.04 | 33 | 51.9 | 32.2 | — | 29.9 | 39.7 | 43.6 | 11 | 36.4 | 40.7 | 27 | 11.8 | 30.3 | 35.3 | 55.9 | 42.2 | 20.8 | 30.1 | 34.5 | 41.2 | 34 | 3.4 | |
| DAF + CPBackbone=ResNet-50, Resolution=600, Noisy Rate (NR)=60%2022.04 | 32.2 | 42.1 | 31.5 | 26.3 | 31.9 | 42.4 | 40.5 | 2.7 | 31.8 | 45.2 | 20 | 12.2 | 26.5 | 38.1 | 51.1 | 42.3 | 11 | 25.6 | 38.4 | 41.4 | 31.7 | 1.1 | |
| DAFBackbone=ResNet-50, Resolution=600, Noisy Rate (NR)=60%2022.04 | 29.4 | 33.5 | 29.7 | 29 | 27.7 | 39.5 | 38 | 2.7 | 31.9 | 41.5 | 19.8 | 12.9 | 30.2 | 37 | 49.7 | 37.2 | 12.8 | 25.5 | 40.8 | 44.2 | 30.6 | 0 | |
| DAF + GCEBackbone=ResNet-50, Resolution=600, Noisy Rate (NR)=60%2022.04 | 26.7 | 43.3 | 33 | 28.6 | 33.8 | 51.8 | 38 | 6.3 | 33.8 | 41.7 | 22.2 | 13.9 | 33.4 | 44.9 | 53.1 | 43.9 | 14.5 | 22.8 | 38.6 | 43.7 | 33.3 | 2.7 | |
| DAF + SCEBackbone=ResNet-50, Resolution=600, Noisy Rate (NR)=60%2022.04 | 22.2 | 44 | 31.3 | 28 | 29.8 | 48.7 | 31.6 | 11 | 29.1 | 30.7 | 19.7 | 9.2 | 25.8 | 55.9 | 51.9 | 41.3 | 5.7 | 21.8 | 49 | 34.9 | 31.1 | 0.5 |