Object Detection on MS-COCO 10% labeled protocol
34.82mAPVirtual Category Learning (with tricks)
Evaluation Results
| Method | Links | |
|---|---|---|
| Virtual Category Learning (with tricks)Configuration=Training tricks in Soft Teacher2022.07 | 34.82 | |
| Soft Teacher2022.07 | 34.04 | |
| Virtual Category LearningConfiguration=Same settings as Unbiased Teacher2022.07 | 33.45 | |
| Combating Noise2022.07 | 32.43 | |
| Humble Teacher2022.07 | 31.61 | |
| Unbiased Teacher2022.07 | 31.5 | |
| Interactive2022.07 | 30.53 | |
| Instant-Teaching*Backbone=R50-FPN, co-rectify scheme=true2021.03 | 30.4 | |
| Instant Teaching2022.07 | 30.4 | |
| Instant-TeachingBackbone=R50-FPN, co-rectify scheme=false2021.03 | 29.45 | |
| STACBackbone=ResNet-50 with FPN, Augmentation=C+{B,G}+Cutout, Training Data=Semi-supervised2020.05 | 28.64 | |
| STACBackbone=R50-FPN2021.03 | 28.64 | |
| STAC2022.07 | 28.64 | |
| Supervised†Backbone=ResNet-50 with FPN, Augmentation=C+{B,G}+Cutout, Training Data=Labeled data only2020.05 | 26.18 | |
| CSD†Backbone=R50-FPN2021.03 | 24.5 | |
| SupervisedBackbone=ResNet-50 with FPN, Augmentation=Standard, Training Data=Labeled data only2020.05 | 23.86 | |
| SupervisedBackbone=R50-FPN2021.03 | 23.86 | |
| Supervised2022.07 | 23.86 | |
| CSD2022.07 | 22.46 |