Object Localization on PASCAL VOC 2007 (trainval)
71.4CorLocPred Net
Evaluation results
| Method | Links | ||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Pred NetMode=Ensemble2018.11 | 71.4 | 89.2 | 86.7 | 72.2 | 50.9 | 51.8 | 88.3 | 89.5 | 65.6 | 33.6 | 87.4 | 59.7 | 66.4 | 88.5 | 94.6 | 30.4 | 60.2 | 83.8 | 68.9 | 78.9 | 81.3 | — | |
| WSOD2Multi-scale testing=true, Train Split=VOC 07+122019.09 | 71.4 | 89.6 | 82.4 | 79.9 | 63.3 | 40.1 | 82.7 | 85 | 62.8 | 45.8 | 89.7 | 52.1 | 70.9 | 88.8 | 91.6 | 37 | 56.4 | 85.6 | 64.3 | 74.1 | 85.3 | — | |
| Pred NetBackbone=VGG2018.11 | 70.9 | 88.6 | 86.3 | 71.8 | 53.4 | 51.2 | 87.6 | 89 | 65.3 | 33.2 | 86.6 | 58.8 | 65.9 | 87.7 | 93.3 | 30.9 | 58.9 | 83.4 | 67.8 | 78.7 | 80.2 | — | |
| Pred NetDetector=Fast R-CNN2020.02 | 70.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Pred Net2020.10 | 70.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CASD2020.10 | 70.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| W2F2018.11 | 70.3 | 85.4 | 87.5 | 62.5 | 54.3 | 35.5 | 85.3 | 86.6 | 82.3 | 39.7 | 82.9 | 49.4 | 76.5 | 74.8 | 90 | 46.8 | 53.9 | 84.5 | 68.3 | 79.1 | 79.9 | — | |
| WSOD2Multi-scale testing=true, Train Split=VOC 20072019.09 | 69.5 | 87.1 | 80 | 74.8 | 60.1 | 36.6 | 79.2 | 83.8 | 70.6 | 43.5 | 88.4 | 46 | 74.7 | 87.4 | 90.8 | 44.2 | 52.4 | 81.4 | 61.8 | 67.7 | 79.9 | — | |
| WSOD2Regression=Included2020.10 | 69.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SDCNDetector=Fast R-CNN2020.02 | 68.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| OIMDetector=Fast R-CNN, Instance Reweighted (IR)=true2020.02 | 68.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MISTRegression=Included2020.10 | 68.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| C-MIDN2020.10 | 68.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ML-LocNet2018.11 | 68.6 | 81.7 | 82.9 | 68.7 | 44.4 | 53.9 | 80.3 | 88.9 | 70.5 | 32.6 | 74 | 62.7 | 61.7 | 81.4 | 91.6 | 46 | 60.6 | 75.2 | 69.2 | 78.7 | 65.8 | — | |
| WS-JDSDetector=Fast R-CNN2020.02 | 68.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| WS-RPN2018.11 | 68.4 | 83.8 | 82.7 | 60.7 | 35.1 | 53.8 | 82.7 | 88.6 | 67.4 | 22 | 86.3 | 68.8 | 50.9 | 90.8 | 93.6 | 44 | 61.2 | 82.5 | 65.9 | 71.1 | 76.7 | — | |
| Label-PEnetLearning type=weakly-supervised2019.10 | 68.2 | 89.8 | 82.6 | 75.3 | 65.7 | 39.2 | 80.2 | 81.6 | 77.7 | 18.4 | 82.7 | 49.3 | 75 | 86.9 | 85.9 | 30.7 | 49.6 | 75.3 | 71.5 | 76.1 | 70.6 | — | |
| OIMDetector=None, Instance Reweighted (IR)=true2020.02 | 67.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MEFF+FRCNNLearning type=weakly-supervised2019.10 | 67 | 88.3 | 77.6 | 74.8 | 63.3 | 37.8 | 78.2 | 83.6 | 72.7 | 19.4 | 79.5 | 46.4 | 78.1 | 83.7 | 90.4 | 21.4 | 43.6 | 76.3 | 68.3 | 77.9 | 70.6 | — | |
| SDCNDetector=None2020.02 | 66.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| OursBackbone=VGG162019.08 | 66.7 | 85.5 | 79.6 | 68.1 | 55.1 | 33.6 | 83.5 | 83.1 | 78.5 | 42.7 | 79.8 | 37.8 | 61.5 | 74.4 | 88.6 | 32.6 | 55.7 | 77.9 | 63.7 | 78.4 | 74.1 | — | |
| OICRDetector=None, W-RPN=true2020.02 | 66.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| C-WSL*Detector=Fast R-CNN2020.02 | 66.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MSPLDFull image-level labels usage=false2017.06 | 65.5 | 66 | 71.2 | 67.9 | 49.7 | 52.9 | 68.8 | 82.6 | 76.6 | 42.5 | 81.6 | 24 | 75.5 | 78.4 | 89 | 62 | 33.1 | 79.2 | 58.5 | 78.9 | 71.1 | — | |
| k-EM2018.11 | 65 | 79.8 | 77.8 | 66.7 | 50.3 | 57 | 80.1 | 89.9 | 71.5 | 29.9 | 75.9 | 30.5 | 58.9 | 73.2 | 90.2 | 25.4 | 51.8 | 80.2 | 60.3 | 72.4 | 78.9 | — | |
| C-MILCNN=VGG162019.04 | 65 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| C-MILDetector=None2020.02 | 65 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| C-MIL2020.10 | 65 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CL2018.11 | 64.7 | 85.8 | 80.4 | 73 | 42.6 | 36.6 | 79.7 | 82.8 | 66 | 34.1 | 78.1 | 36.9 | 68.6 | 72.4 | 91.6 | 22.2 | 51.3 | 79.4 | 63.7 | 74.5 | 74.6 | — | |
| WSCDNMulti-scale testing=true, Train Split=VOC 20072019.09 | 64.7 | 85.8 | 80.4 | 73 | 42.6 | 36.6 | 79.7 | 82.8 | 66 | 34.1 | 78.1 | 36.9 | 51.3 | 79.4 | 63.7 | 51.3 | 79.4 | 63.7 | 74.5 | 74.6 | 22.2 | — | |
| Teh et al.Full image-level labels usage=true2017.06 | 64.6 | 84 | 64.6 | 70 | 62.4 | 25.8 | 80.6 | 73.9 | 71.5 | 35.7 | 81.6 | 46.5 | 71.2 | 79.1 | 78.8 | 56.7 | 34.3 | 69.8 | 56.7 | 77 | 72.7 | — | |
| Teh et al.Backbone=VGG162019.08 | 64.6 | 84 | 64.6 | 70 | 62.4 | 25.8 | 80.7 | 73.9 | 71.5 | 35.7 | 81.6 | 46.5 | 71.3 | 79.1 | 78.8 | 56.7 | 34.3 | 69.8 | 56.7 | 77 | 72.7 | — | |
| WS-JDSDetector=None2020.02 | 64.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| OICR-Ens.+FRCNNEnsemble=true, Detector=Fast R-CNN2017.04 | 64.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Tang et al.Full image-level labels usage=true2017.06 | 64.3 | 85.8 | 82.7 | 62.8 | 45.2 | 43.5 | 84.8 | 87 | 46.8 | 15.7 | 82.2 | 51 | 45.6 | 83.7 | 91.2 | 22.2 | 59.7 | 75.3 | 65.1 | 76.8 | 78.1 | — | |
| OICR2018.11 | 64.3 | 85.8 | 82.7 | 62.8 | 45.2 | 43.5 | 84.8 | 87 | 46.8 | 15.7 | 82.2 | 51 | 45.6 | 83.7 | 91.2 | 22.2 | 59.7 | 75.3 | 65.1 | 76.8 | 78.1 | — | |
| OICR-Ens+FRCNNLearning type=weakly-supervised2019.10 | 64.3 | 85.8 | 82.7 | 62.8 | 45.2 | 43.5 | 84.8 | 87 | 46.8 | 15.7 | 82.2 | 51 | 45.6 | 78.1 | 91.2 | 22.2 | 59.7 | 75.3 | 65.1 | 76.8 | 78.1 | — | |
| WeakRPNCNN=VGG162019.04 | 63.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| WSRPNBackbone=VGG162019.08 | 63.8 | 77.5 | 81.2 | 55.3 | 19.7 | 44.3 | 80.2 | 86.6 | 69.5 | 10.1 | 87.7 | 68.4 | 52.1 | 84.4 | 91.6 | 57.4 | 63.4 | 77.3 | 58.1 | 57 | 53.8 | — | |
| Tang et al.Multi-scale testing=true, Train Split=VOC 20072019.09 | 63.8 | 77.5 | 81.2 | 55.3 | 19.7 | 44.3 | 80.2 | 86.6 | 69.5 | 10.1 | 87.7 | 68.4 | 52.1 | 84.4 | 91.6 | 57.4 | 63.4 | 77.3 | 58.1 | 57 | 53.8 | — | |
| C-WSLMulti-scale testing=true, Train Split=VOC 20072019.09 | 63.5 | 85.8 | 81.2 | 64.9 | 50.5 | 32.1 | 84.3 | 85.9 | 54.7 | 43.4 | 80.1 | 42.2 | 42.6 | 60.5 | 90.4 | 13.7 | 57.5 | 82.5 | 61.8 | 74.1 | 82.4 | — | |
| C-WSL*Detector=None2020.02 | 63.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SGWSODBackbone=VGG162019.08 | 62.9 | 71 | 76.5 | 54.9 | 49.7 | 54.1 | 78 | 87.4 | 68.8 | 32.4 | 75.2 | 29.5 | 58 | 67.3 | 84.5 | 41.5 | 49 | 78.1 | 60.3 | 62.8 | 78.9 | — | |
| SPL+EnsembleDetection model=Ensemble, Backbone=VGG16 + ResNet50-OHEM + ResNet101, Full image-level labels usage=false2017.06 | 62.7 | 54.6 | 65 | 71.2 | 50.8 | 52.1 | 62.4 | 81.9 | 67.7 | 41.4 | 74.5 | 21 | 69.6 | 78.4 | 86.5 | 66.5 | 46.1 | 76 | 57.6 | 74.7 | 56.3 | — | |
| PCLMulti-scale testing=true, Train Split=VOC 20072019.09 | 62.7 | 79.6 | 85.5 | 62.2 | 47.9 | 37 | 83.8 | 83.4 | 43 | 38.3 | 80.1 | 50.6 | 30.9 | 57.8 | 90.8 | 27 | 58.2 | 75.3 | 68.5 | 75.7 | 78.9 | — | |
| PCLDetector=None2020.02 | 62.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| PCL2020.10 | 62.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MELMCNN=VGG162019.02 | 61.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MELMDetector=None2020.02 | 61.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| OICR-Ens.Ensemble=true2017.04 | 61.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ZLDN-Lvariant=L2018.04 | 61.2 | 74 | 77.8 | 65.2 | 37 | 46.7 | 75.8 | 83.7 | 58.8 | 17.5 | 73.1 | 49 | 51.3 | 76.7 | 87.4 | 30.6 | 47.8 | 75 | 62.5 | 64.8 | 68.8 | — | |
| ZLDN2018.11 | 61.2 | 74 | 77.8 | 65.2 | 37 | 46.7 | 75.8 | 83.7 | 58.8 | 17.5 | 73.1 | 49 | 51.3 | 76.7 | 87.4 | 30.6 | 47.8 | 75 | 62.5 | 64.8 | 68.8 | — | |
| ZLDNMulti-scale testing=true, Train Split=VOC 20072019.09 | 61.2 | 74 | 77.8 | 65.2 | 37 | 46.7 | 75.8 | 83.7 | 58.8 | 17.5 | 73.1 | 49 | 51.3 | 76.7 | 87.4 | 30.6 | 47.8 | 75 | 62.5 | 64.8 | 68.8 | — | |
| TS2CCNN=VGG162019.04 | 61 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| TS2CBackbone=VGG162019.08 | 61 | 84.2 | 74.1 | 61.3 | 52.1 | 32.1 | 76.7 | 82.9 | 66.6 | 42.3 | 70.6 | 39.5 | 57 | 61.2 | 88.4 | 9.3 | 54.6 | 72.2 | 60 | 65 | 70.3 | — | |
| Dong et al.Full image-level labels usage=true2017.06 | 60.9 | 85.3 | 71.9 | 66.8 | 27 | 26.5 | 81.2 | 78.5 | 36.1 | 17.2 | 80.6 | 61.8 | 76.1 | 86.3 | 83.6 | 22.2 | 43.6 | 74.8 | 60.6 | 67.6 | 70.5 | — | |
| OICR-VGG16Backbone=VGG16, Ensemble=false2017.04 | 60.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SP-VGGNetBackbone=VGGNet2017.09 | 60.6 | 85.3 | 64.2 | 67 | 42 | 16.4 | 71 | 64.7 | 88.7 | 20.7 | 63.8 | 58 | 84.1 | 84.7 | 80 | 60 | 29.4 | 56.3 | 68.1 | 77.4 | 30.5 | — | |
| OICR2018.04 | 60.6 | 81.7 | 80.4 | 48.7 | 49.5 | 32.8 | 81.7 | 85.4 | 40.1 | 40.6 | 79.5 | 35.7 | 33.7 | 60.5 | 88.8 | 21.8 | 57.9 | 76.3 | 59.9 | 75.3 | 81.4 | — | |
| Zhu et al.Full image-level labels usage=true2017.06 | 60.6 | 85.3 | 64.2 | 67 | 42 | 16.4 | 71 | 64.7 | 88.7 | 20.7 | 63.8 | 58 | 84.1 | 84.7 | 80 | 60 | 29.4 | 56.3 | 68.1 | 77.4 | 30.5 | — | |
| OICRCNN=VGG162019.04 | 60.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| OICRBackbone=VGG162019.08 | 60.6 | 81.7 | 80.4 | 48.7 | 49.5 | 32.8 | 81.7 | 85.4 | 40.1 | 40.6 | 79.5 | 35.7 | 33.7 | 60.5 | 88.8 | 21.8 | 57.9 | 76.3 | 59.9 | 75.3 | 81.4 | — | |
| OICRMulti-scale testing=true, Train Split=VOC 20072019.09 | 60.6 | 81.7 | 80.4 | 48.7 | 49.5 | 32.8 | 81.7 | 85.4 | 40.1 | 40.6 | 79.5 | 35.7 | 33.7 | 60.5 | 88.8 | 21.8 | 57.9 | 76.3 | 59.9 | 75.3 | 81.4 | — | |
| OICRDetector=None2020.02 | 60.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| OICR-VGG16Learning type=weakly-supervised2019.10 | 60.6 | 81.7 | 80.4 | 48.7 | 49.5 | 32.8 | 81.7 | 85.4 | 40.1 | 40.6 | 79.5 | 35.7 | 33.7 | 60.5 | 88.8 | 21.8 | 57.9 | 76.3 | 59.9 | 75.3 | 81.4 | — | |
| OICR2020.10 | 60.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SPL+Fast R-CNNDetection model=Fast R-CNN, Backbone=VGG16, Full image-level labels usage=false2017.06 | 58.8 | 63.3 | 72.3 | 49.6 | 43.8 | 42.4 | 54.4 | 78.7 | 58.1 | 35.4 | 72.8 | 43 | 63.1 | 78.1 | 82.3 | 59.1 | 37.8 | 68.8 | 56.6 | 64.5 | 51.7 | — | |
| MELMCNN=VGGF/AlexNet2019.02 | 58.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| WSDDN-Ens.Ensemble=true2017.04 | 58 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| WSDDN2018.11 | 58 | 68.9 | 68.7 | 65.2 | 42.5 | 40.6 | 72.6 | 75.2 | 53.7 | 29.7 | 68.1 | 33.5 | 45.6 | 65.9 | 86.1 | 27.5 | 44.9 | 76 | 62.4 | 66.3 | 66.8 | — | |
| WSDDN-EnsLearning type=weakly-supervised2019.10 | 58 | 68.9 | 68.7 | 65.2 | 42.5 | 40.6 | 72.6 | 75.2 | 53.7 | 29.7 | 68.1 | 33.5 | 45.6 | 65.9 | 86.1 | 27.5 | 44.9 | 76 | 62.4 | 66.3 | 66.8 | — | |
| ZLDN-Svariant=S2018.04 | 57.8 | 74.8 | 69.1 | 60.3 | 35.9 | 38.1 | 66.7 | 80.2 | 60.5 | 15.7 | 71.6 | 45.5 | 54.4 | 72.8 | 86.1 | 31.2 | 42 | 64.6 | 60.3 | 58.6 | 66.4 | — | |
| OICR-VGG_MBackbone=VGG_M, Ensemble=false2017.04 | 57.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Diba et al.Full image-level labels usage=true2017.06 | 56.7 | 83.9 | 72.8 | 64.5 | 44.1 | 40.1 | 65.7 | 82.5 | 58.9 | 33.7 | 72.5 | 25.6 | 53.7 | 67.4 | 77.4 | 26.8 | 49.1 | 68.1 | 27.9 | 64.5 | 55.7 | — | |
| WSCCN2018.11 | 56.7 | 83.9 | 72.8 | 64.5 | 44.1 | 40.1 | 65.7 | 82.5 | 58.9 | 33.7 | 72.5 | 25.6 | 53.7 | 67.4 | 77.4 | 26.8 | 49.1 | 68.1 | 27.9 | 64.5 | 55.7 | — | |
| WCCNCNN=VGG162019.02 | 56.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| WCCNCNN=VGG162019.04 | 56.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| WSDDN-VGG_MBackbone=VGG_M, Ensemble=false2017.04 | 56.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DSD2018.04 | 56.1 | 72.7 | 55.3 | 53 | 27.8 | 35.2 | 68.6 | 81.9 | 60.7 | 11.6 | 71.6 | 29.7 | 54.3 | 64.3 | 88.2 | 22.2 | 53.7 | 72.2 | 52.6 | 68.9 | 75.5 | — | |
| contrastive SBackbone=VGG-F, Proposals=Selective Search, Ratio=1.8, Evaluation=Multi-scale and flips2016.09 | 55.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| WSDDN+contextEnsemble=false, Context=true2017.04 | 55.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ContextLoc2017.09 | 55.1 | 83.3 | 68.6 | 54.7 | 23.4 | 18.3 | 73.6 | 74.1 | 54.1 | 8.6 | 65.1 | 47.1 | 59.5 | 67 | 83.5 | 35.3 | 39.9 | 67 | 49.7 | 63.5 | 65.2 | — | |
| Kantorov et al.Full image-level labels usage=true2017.06 | 55.1 | 83.3 | 68.6 | 54.7 | 23.4 | 18.3 | 73.6 | 74.1 | 54.1 | 8.6 | 65.1 | 47.1 | 59.5 | 67 | 83.5 | 35.3 | 39.9 | 67 | 49.7 | 63.5 | 65.2 | — | |
| ContextNetCNN=VGGF/AlexNet2019.02 | 55.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ContextLocNetMulti-scale testing=true, Train Split=VOC 20072019.09 | 55.1 | 83.3 | 68.6 | 54.7 | 23.4 | 18.3 | 73.6 | 74.1 | 54.1 | 8.6 | 65.1 | 47.1 | 59.5 | 67 | 83.5 | 35.3 | 39.9 | 67 | 49.7 | 63.5 | 65.2 | — | |
| HCP+DSD+OSSH3Learning type=weakly-supervised2019.10 | 54.9 | 72.2 | 55.3 | 53 | 27.8 | 35.2 | 68.6 | 81.9 | 60.7 | 11.6 | 71.6 | 29.7 | 54.3 | 64.3 | 88.2 | 22.2 | 53.7 | 72.2 | 52.6 | 68.9 | 74.4 | — | |
| WSDDN-SSW-ENSType=Ensemble2016.09 | 54.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| WSDDN-VGG_FBackbone=VGG_F, Ensemble=false2017.04 | 54.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Multi-fold MILCNN=VGGF/AlexNet2019.02 | 54.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| WSDDNCNN=VGGF/AlexNet2019.02 | 54.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Bilen et al.Full image-level labels usage=true2017.06 | 53.8 | 73.1 | 68.7 | 52.4 | 34.3 | 26.6 | 66.1 | 76.7 | 51.6 | 15.1 | 66.7 | 17.5 | 45.4 | 71.8 | 82.4 | 32.6 | 42.9 | 71.9 | 53.3 | 60.9 | 65.2 | — | |
| WSDDN-VGG16Backbone=VGG16, Ensemble=false2017.04 | 53.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| WSDDN2017.09 | 53.5 | 65.1 | 58.8 | 58.5 | 33.1 | 39.8 | 68.3 | 60.2 | 59.6 | 34.8 | 64.5 | 30.5 | 43 | 56.8 | 82.4 | 25.5 | 41.6 | 61.5 | 55.9 | 65.9 | 63.7 | — | |
| WSDDN2018.04 | 53.5 | 65.1 | 58.8 | 58.5 | 33.1 | 39.8 | 68.3 | 60.2 | 59.6 | 34.8 | 64.5 | 30.5 | 43 | 56.8 | 82.4 | 25.5 | 41.6 | 61.5 | 55.9 | 65.9 | 63.7 | — | |
| WSDDNCNN=VGG162019.02 | 53.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| WSDDNCNN=VGG162019.04 | 53.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| WSDDNMulti-scale testing=true, Train Split=VOC 20072019.09 | 53.5 | 65.1 | 58.8 | 58.5 | 33.1 | 39.8 | 68.3 | 60.2 | 59.6 | 34.8 | 64.5 | 30.5 | 43 | 56.8 | 82.4 | 25.5 | 41.6 | 61.5 | 55.9 | 65.9 | 63.7 | — | |
| WSDDN2020.10 | 53.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SPL+R-FCNDetection model=R-FCN, Backbone=ResNet50-OHEM, Full image-level labels usage=false2017.06 | 53.2 | 39.2 | 54.8 | 59 | 38.6 | 34.5 | 53.7 | 73.7 | 62.2 | 36.2 | 73.6 | 8 | 61.8 | 75.1 | 78.9 | 57.1 | 22.1 | 75.5 | 45.5 | 67.9 | 47.4 | — | |
| additiveBackbone=VGG-F, Proposals=Selective Search, Ratio=1.8, Evaluation=Multi-scale and flips2016.09 | 52.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |