| Paper | Code | mIoU | mIoU (Temporal DA) | mIoU (Env DA) | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|
| Masked-attention Mask Transformer for Universal Image Segmentation | ✓ Link | 47.85 | Mask2Former (Swin-L) | 2021-12-02 | ||
| Unified Perceptual Parsing for Scene Understanding | ✓ Link | 47.30 | UPerNet (ConvNeXt-L) | 2018-07-26 | ||
| Masked-attention Mask Transformer for Universal Image Segmentation | ✓ Link | 43.71 | Mask2Former (ResNet-50) | 2021-12-02 | ||
| Rethinking Atrous Convolution for Semantic Image Segmentation | ✓ Link | 43.37 | 43.95 | 36.12 | DeepLabv3 (ResNet-50) | 2017-06-17 |
| SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers | ✓ Link | 40.83 | Segformer (MiT-B5) | 2021-05-31 |