Semantic Segmentation on SUN-RGBD 37 classes (test)
50.6mIoUPSD
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| PSDCategory=multi-task encoder-decoder, Data=RGB, Backbone=ResNet-50, Scale=single-scale inference2022.01 | 50.6 | 84 | 57.3 | |
| PAPCategory=multi-task encoder-decoder, Data=RGB, Backbone=ResNet-50, Scale=single-scale inference2022.01 | 50.5 | 83.8 | 58.4 | |
| TRLCategory=multi-task encoder-decoder, Data=RGB, Backbone=ResNet-50, Scale=single-scale inference2022.01 | 49.6 | 83.6 | 58.2 | |
| ADSDCategory=encoder-decoder, Data=RGBD, Backbone=ResNet-50, Scale=single-scale inference2022.01 | 49.6 | 81.8 | 62.1 | |
| SA-GateCategory=encoder-decoder, Data=RGBD, Backbone=ResNet-101, Scale=multi-scale inference2022.01 | 49.4 | — | — | |
| CANetCategory=encoder-decoder, Data=RGBD, Backbone=ResNet-101, Scale=single-scale inference2022.01 | 49.3 | 82.5 | 60.5 | |
| ESANetCategory=encoder-decoder, Data=RGBD, Backbone=ResNet-50, Scale=single-scale inference2022.01 | 48.3 | — | — | |
| ACNetCategory=encoder-decoder, Data=RGBD, Backbone=ResNet-50, Scale=single-scale inference2022.01 | 48.1 | — | 60.3 | |
| RedNetCategory=encoder-decoder, Data=RGBD, Backbone=ResNet-50, Scale=single-scale inference2022.01 | 47.8 | 81.3 | 60.3 | |
| RDFNet-152Category=encoder-decoder, Data=RGB, Backbone=ResNet-152, Scale=multi-scale inference2022.01 | 47.7 | 81.5 | 60.1 | |
| SGNetCategory=encoder-decoder, Data=RGBD, Backbone=ResNet-101, Scale=single-scale inference2022.01 | 47.1 | 81 | 59.6 | |
| RefineNetCategory=atrous/dilated convolution, Data=RGB, Backbone=ResNet-152, Scale=multi-scale inference2022.01 | 47 | 81.1 | 57.7 | |
| RefineNetTrain data=RGB, Backbone=ResNet-1522016.11 | 45.9 | 80.6 | 58.5 | |
| RefineNetTrain data=RGB, Backbone=ResNet-1012016.11 | 45.7 | 80.4 | 57.8 | |
| PU-LoopCategory=multi-task encoder-decoder, Data=RGB, Backbone=ResNet-50, Scale=single-scale inference2022.01 | 45.1 | 80.3 | — | |
| CFNCategory=atrous/dilated convolution, Data=RGBD, Backbone=VGG-16, Scale=multi-scale inference2022.01 | 42.5 | — | — | |
| ContextTrain data=RGB2016.11 | 42.3 | 78.4 | 53.4 | |
| 3DGNNCategory=atrous/dilated convolution, Data=RGBD, Backbone=VGG-16, Scale=multi-scale inference2022.01 | 42.3 | — | 54.6 | |
| D-CNNCategory=atrous/dilated convolution, Data=RGBD, Backbone=VGG-16, Scale=single-scale inference2022.01 | 42 | — | 53.5 | |
| FuseNetCategory=encoder-decoder, Data=RGBD, Backbone=VGG-16, Scale=single-scale inference2022.01 | 37.3 | 76.3 | 48.3 | |
| Ren et al.Train data=RGB-D2016.11 | 36.3 | — | — | |
| DeepLab-LFOVCategory=atrous/dilated convolution, Data=RGBD, Backbone=VGG-16, Scale=multi-scale inference2022.01 | 32.1 | 71.9 | 42.2 | |
| SegNetCategory=encoder-decoder, Data=RGB, Backbone=VGG-16, Scale=single-scale inference2022.01 | 31.8 | 72.6 | 44.8 | |
| Kendall et al.Train data=RGB2016.11 | 30.7 | 71.2 | 45.9 | |
| B-SegNetCategory=encoder-decoder, Data=RGB, Backbone=VGG-16, Scale=single-scale inference2022.01 | 30.7 | 71.2 | 45.9 | |
| FCNCategory=encoder-decoder, Data=RGBD, Backbone=VGG-16, Scale=single-scale inference2022.01 | 27.4 | 68.2 | 38.4 | |
| DeconvNetCategory=encoder-decoder, Data=RGB, Backbone=VGG-16, Scale=single-scale inference2022.01 | 22.6 | 66.1 | 32.3 | |
| Liu et al.Train data=RGB-D2016.11 | 10 | — | — | |
| LSD-GFCategory=encoder-decoder, Data=RGBD, Backbone=VGG-16, Scale=single-scale inference2022.01 | — | — | 58 |