Object Detection on PASCAL VOC 2012 (val)
81.9Mean AP^bFast RCNN
Evaluation results
| Method | Links | |||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Fast RCNNBBox=Yes2015.11 | 81.9 | — | 95.2 | 88.2 | 88.4 | 77.9 | 49 | 93.4 | 83.6 | 95.1 | 59.4 | 86.6 | — | 71 | 92.6 | 93.1 | 93 | 92.2 | 58.2 | 88 | 63.6 | 91.9 | 77.3 | |
| Proposed MethodBackbone=VGG-162016.03 | 79.7 | — | 90.1 | 86.4 | 86.1 | 77.6 | 56.8 | 90.3 | 68.3 | 89.9 | 54.7 | 86.8 | 66.4 | — | 88.5 | 89 | 88.1 | 78.5 | 64.1 | 90 | 67 | 89.9 | 82.6 | |
| ProNet (Cascade)BBox=No2015.11 | 77.7 | — | 92.6 | 85.6 | 87.4 | 79.6 | 48.3 | 88.7 | 68.9 | 94.2 | 54.6 | 83.2 | — | 62.8 | 92 | 89.9 | 88.2 | 87.1 | 49.2 | 86.9 | 57.2 | 86.8 | 70 | |
| Proposed MethodBackbone=Alexnet2016.03 | 77.1 | — | 90 | 81.2 | 81.2 | 82.2 | 47.5 | 86.7 | 64.9 | 85.7 | 53.9 | 75.8 | 67.9 | — | 82.2 | 84.1 | 83.4 | 83.9 | 71.7 | 83.1 | 63.7 | 89.4 | 78.2 | |
| RCNN*2016.03 | 74.8 | — | 92 | 80.8 | 80.8 | 73 | 49.9 | 86.8 | 77.7 | 87.6 | 50.4 | 72.1 | 57.6 | — | 82.9 | 79.1 | 89.8 | 88.1 | 56.1 | 83.5 | 50.1 | 82 | 76.6 | |
| RCNNBBox=Yes2015.11 | 74.8 | — | 92 | 80.8 | 80.8 | 73 | 49.9 | 86.8 | 77.7 | 87.6 | 50.4 | 72.1 | — | 57.6 | 82.9 | 79.1 | 89.8 | 88.1 | 56.1 | 83.5 | 50.1 | 81.5 | 76.6 | |
| ProNet (Proposal)BBox=No2015.11 | 74.8 | — | 91.6 | 82 | 85.1 | 78.6 | 45.9 | 87.9 | 67.1 | 92.2 | 51 | 72.9 | — | 60.8 | 89.3 | 85.1 | 85.3 | 86.4 | 45.6 | 83.5 | 55.1 | 85.6 | 65.9 | |
| Oquab et al.2016.03 | 74.5 | — | 90.3 | 77.4 | 77.4 | 79.2 | 41.1 | 87.8 | 66.4 | 91 | 47.3 | 83.7 | 55.1 | — | 88.8 | 93.6 | 85.2 | 87.4 | 43.5 | 86.2 | 50.8 | 86.8 | 66.5 | |
| Oquab et al.BBox=No2015.11 | 74.5 | — | 90.3 | 77.4 | 81.4 | 79.2 | 41.4 | 87.8 | 66.4 | 91 | 47.3 | 83.7 | — | 55.1 | 88.8 | 93.6 | 85.2 | 87.4 | 43.5 | 86.2 | 50.8 | 86.8 | 66.5 | |
| IE-CLBackbone=ResNet-50, Architecture=Faster R-CNN2026.03 | 74.41 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MoCo-v2Backbone=ResNet-50, Architecture=Faster R-CNN2026.03 | 73.92 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SupervisedBackbone=ResNet-50, Architecture=Faster R-CNN2026.03 | 73.76 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SimSiamBackbone=ResNet-50, Architecture=Faster R-CNN2026.03 | 73.45 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SimCLRBackbone=ResNet-50, Architecture=Faster R-CNN2026.03 | 73.17 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Fast-RCNN*2016.03 | 71.3 | — | 79.2 | 74.7 | 74.7 | 65.8 | 39.4 | 82.3 | 64.8 | 85.7 | 54.5 | 77.2 | 58.8 | — | 85.1 | 86.1 | 80.5 | 76.6 | 46.7 | 79.5 | 68.3 | 85 | 60 | |
| B2014.07 | 53.9 | 44.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| C2014.07 | 53 | 44.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| A2014.07 | 51.9 | 43.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| R-CNN-MCG2014.07 | 51.7 | 42.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| R-CNN2014.07 | 51 | 41.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| OIM+IRdataset_config=train/val2020.02 | 44.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| C-WSLdataset_config=train/val2020.02 | 43 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| RandomBackbone=ResNet-50, Architecture=Faster R-CNN2026.03 | 40.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MELMdataset_config=train/val2020.02 | 40.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| HCP+DSD+OSSH3+NRDSD=true, OSSH=2nd, 3rd and 4th epochs, NR=true2017.04 | 39 | — | 60.9 | 53.3 | 31 | 16.4 | 18.2 | 58.2 | 50.5 | 55.6 | 9.1 | 42.1 | — | 12.1 | 43.4 | 45.3 | 64.6 | 7.4 | 19.3 | 44.8 | 39.3 | 51.4 | 57.2 | |
| HCP+DSD+OSSH3DSD=true, OSSH=2nd, 3rd and 4th epochs2017.04 | 38.5 | — | 61 | 53.8 | 30.3 | 18.1 | 18.6 | 57.4 | 51.1 | 53.1 | 6.1 | 40.7 | — | 12.1 | 38.2 | 48.2 | 65.5 | 4.8 | 20.9 | 45.5 | 34 | 54.1 | 57.3 | |
| HCP+DSD+OSSH2DSD=true, OSSH=2nd and 3rd epochs2017.04 | 38.4 | — | 57.7 | 55.9 | 34.8 | 17.4 | 18.3 | 57.8 | 48.6 | 51 | 9.7 | 40.8 | — | 7.2 | 42.5 | 47.2 | 62.2 | 4.6 | 18.4 | 43 | 36.8 | 55.7 | 57.8 | |
| HCP+DSD+OSSH1DSD=true, OSSH=2nd epoch only2017.04 | 36.5 | — | 60.7 | 54 | 36.5 | 14.4 | 19.5 | 57.5 | 45.5 | 47.7 | 11.1 | 39.9 | — | 2.8 | 43.4 | 38.2 | 55.5 | 4.3 | 18.6 | 40.5 | 31.1 | 56.6 | 52 | |
| Li et al.2017.04 | 29.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| HCP+DSDDSD=true2017.04 | 28.3 | — | 55.3 | 39.3 | 25.3 | 14.3 | 10.6 | 50.4 | 35.6 | 45.4 | 11.4 | 31.3 | — | 2.3 | 30.6 | 29.7 | 35.3 | 5 | 14.2 | 28.1 | 13.8 | 47.1 | 41.1 | |
| Weakly Supervised Localization using Deep Feature MapsBackbone=VGG-162016.03 | 26.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| HCP2017.04 | 24.7 | — | 49.3 | 33.3 | 24.7 | 14 | 11.8 | 37.9 | 30.2 | 35.7 | 6.9 | 26.6 | — | 6.9 | 25.4 | 14.1 | 29.4 | 1.1 | 18.1 | 25.7 | 13.4 | 44.1 | 45.4 | |
| Oquab et. al.Search Method=Selective Search2016.03 | 11.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |