Instance Segmentation on LVIS 80 x 80 (test)
0.54IoUFSNet+HRNet
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| FSNet+HRNetDownsampling Strategy=FSNet, Backbone=HRNet, Resolution=80 x 802025.03 | 0.54 | 0.55 | |
| FSNet+SegFormer-B4Downsampling Strategy=FSNet, Backbone=SegFormer-B4, Resolution=80 x 802025.03 | 0.54 | 0.56 | |
| FSNet+SegFormer-B5Downsampling Strategy=FSNet, Backbone=SegFormer-B5, Resolution=80 x 802025.03 | 0.54 | 0.55 | |
| FSNet+DeepLabDownsampling Strategy=FSNet, Backbone=DeepLabV3, Resolution=80 x 802025.03 | 0.53 | 0.55 | |
| LTDDownsampling Strategy=Learn-to-Downsample, Resolution=80 x 802025.03 | 0.4 | 0.41 | |
| Avg+HRNetDownsampling Strategy=Uniform Subsampling, Backbone=HRNet, Resolution=80 x 802025.03 | 0.37 | 0.38 | |
| Avg+SegFormer-B4Downsampling Strategy=Uniform Subsampling, Backbone=SegFormer-B4, Resolution=80 x 802025.03 | 0.37 | 0.38 | |
| Avg+DeepLabDownsampling Strategy=Uniform Subsampling, Backbone=DeepLabV3, Resolution=80 x 802025.03 | 0.35 | 0.36 | |
| Avg+SegFormer-B5Downsampling Strategy=Uniform Subsampling, Backbone=SegFormer-B5, Resolution=80 x 802025.03 | 0.35 | 0.37 |