Object Detection on PASCAL VOC 2010 (test)
68.8mAPFast R-CNN
Evaluation Results
| Method | Links | |||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Fast R-CNNtrain set=07++122015.04 | 68.8 | 82 | 77.8 | 71.6 | 55.3 | 42.4 | 77.3 | 71.7 | 89.3 | 44.5 | 72.1 | 53.7 | 87.7 | 80 | 82.5 | 72.7 | 36.6 | 68.7 | 65.4 | 81.1 | 62.7 | |
| SegDeepMtrain set=12+seg2015.04 | 67.2 | 82.3 | 75.2 | 67.1 | 50.7 | 49.8 | 71.1 | 69.6 | 88.2 | 42.5 | 71.2 | 50 | 85.7 | 76.6 | 81.8 | 69.3 | 41.5 | 71.9 | 62.2 | 73.2 | 64.6 | |
| Fast R-CNNtrain set=122015.04 | 66.1 | 80.1 | 74.4 | 67.7 | 49.4 | 41.4 | 74.2 | 68.8 | 87.8 | 41.9 | 70.1 | 50.2 | 86.1 | 77.3 | 81.1 | 70.4 | 33.3 | 67 | 63.3 | 77.2 | 60 | |
| BabyLearningtrain set=Prop.2015.04 | 63.8 | 77.7 | 73.8 | 62.3 | 48.8 | 45.4 | 67.3 | 67 | 80.3 | 41.3 | 70.8 | 49.7 | 79.5 | 74.7 | 78.6 | 64.5 | 36 | 69.9 | 55.7 | 70.4 | 61.7 | |
| R-CNN BBtrain set=122015.04 | 62.9 | 79.3 | 72.4 | 63.1 | 44 | 44.4 | 64.6 | 66.3 | 84.9 | 38.8 | 67.3 | 48.4 | 82.3 | 75 | 76.7 | 65.7 | 35.8 | 66.2 | 54.8 | 69.1 | 58.8 | |
| R-CNNFine-tuning=true, Feature layer=fc7, Bounding-box regression=true2014.09 | 53.7 | 71.8 | 65.8 | 53 | 36.8 | 35.9 | 59.7 | 60 | 69.9 | 27.9 | 50.6 | 41.4 | 70 | 62 | 69 | 58.1 | 29.5 | 59.4 | 39.3 | 61.2 | 52.4 | |
| R-CNNFine-tuning=true, Feature layer=fc72014.09 | 50.2 | 67.1 | 64.1 | 46.7 | 32 | 30.5 | 56.4 | 57.2 | 65.9 | 27 | 47.3 | 40.9 | 66.6 | 57.8 | 65.9 | 53.6 | 26.7 | 56.5 | 38.1 | 52.8 | 50.2 | |
| Ranking GAN (Ours_VGG)Backbone=VGG, Detection Framework=SSD2017.11 | 43.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DeepPyramid DPMmax_pyramid_levels=52014.09 | 42 | 61 | 55.7 | 36.5 | 20.7 | 33.2 | 52.5 | 46.1 | 48 | 22.1 | 35 | 32.3 | 45.7 | 50.2 | 59.2 | 55.8 | 18.7 | 49.1 | 28.8 | 40.6 | 48.1 | |
| Ranking GAN (Ours_VGG)Backbone=VGG, Detection Framework=FRCNN2017.11 | 41.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SegDPM2014.09 | 40.4 | 61.4 | 53.4 | 25.6 | 25.2 | 35.5 | 51.7 | 50.6 | 50.8 | 19.3 | 33.8 | 26.8 | 40.4 | 48.3 | 54.4 | 47.1 | 14.8 | 38.7 | 35 | 52.8 | 43.1 | |
| Regionlets2014.09 | 39.7 | 65 | 48.9 | 25.9 | 24.6 | 24.5 | 56.1 | 54.5 | 51.2 | 17 | 28.9 | 30.2 | 35.8 | 40.2 | 55.7 | 43.5 | 14.3 | 43.9 | 32.6 | 54 | 45.9 | |
| WCCNBackbone=VGG162017.11 | 39.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| WCCN_3stage_VGG16Backbone=VGG16, Number of Stages=32016.11 | 39.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Jie et al.2017.11 | 38.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Ranking GAN (Ours_AlexNet)Backbone=AlexNet, Detection Framework=FRCNN2017.11 | 38.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| WCCN_2stage_VGG16Backbone=VGG16, Number of Stages=22016.11 | 37.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| WSDDN2017.11 | 36.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| WSDDN2016.11 | 36.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| WSDDN Ensembleconfiguration=Ensemble2015.11 | 36.2 | 57.4 | 51.8 | 41.2 | 16.4 | 22.8 | 57.3 | 41.8 | 34.8 | 13.1 | 37.6 | 10.8 | 37 | 45.2 | 64.9 | 14.1 | 22.3 | 33.8 | 27.6 | 49.1 | 44.8 | |
| UVA2014.09 | 35.1 | 56.2 | 42.4 | 15.3 | 12.6 | 21.8 | 49.3 | 36.8 | 46.1 | 12.9 | 32.1 | 30 | 36.5 | 43.5 | 52.9 | 32.9 | 15.3 | 41.1 | 31.8 | 47 | 44.8 | |
| HOG-DPM2014.09 | 33.4 | 49.2 | 53.8 | 13.1 | 15.3 | 35.5 | 53.4 | 49.7 | 27 | 17.2 | 28.8 | 14.7 | 17.8 | 46.4 | 51.2 | 47.7 | 10.8 | 34.2 | 20.7 | 43.8 | 38.3 | |
| Li et al.Backbone=VGG162017.11 | 30.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Li et al.Backbone=VGG162016.11 | 30.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| WCCN_3stage_AlexnetBackbone=AlexNet, Number of Stages=32016.11 | 28.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| WCCN_2stage_AlexnetBackbone=AlexNet, Number of Stages=22016.11 | 27.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Cinbis et al.2017.11 | 27.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Cinbis et al.2016.11 | 27.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Cinbis et al.2015.11 | 27.4 | 44.6 | 42.3 | 25.5 | 14.1 | 11 | 44.1 | 36.3 | 23.2 | 12.2 | 26.1 | 14 | 29.2 | 36 | 54.3 | 20.7 | 12.4 | 26.5 | 20.3 | 31.2 | 23.7 | |
| Li et al.Backbone=AlexNet2017.11 | 21.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Li et al.Backbone=AlexNet2016.11 | 21.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |