Semantic Segmentation On Mapillary Val
평가 지표
mIoU
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | mIoU | Paper Title | Repository |
|---|---|---|---|
| AO-SegNet | 76.0 | Interactive Learning of Intrinsic and Extrinsic Properties for All-day Semantic Segmentation | |
| Resnet50 | 32.93 | MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation | |
| Mask2Former (Swin-L, multiscale) | 64.7 | Masked-attention Mask Transformer for Universal Image Segmentation | |
| SegBlocks-RN50 (t=0.4) | 39.7 | SegBlocks: Block-Based Dynamic Resolution Networks for Real-Time Segmentation | |
| OneFormer (DiNAT-L, multi-scale) | 64.9 | OneFormer: One Transformer to Rule Universal Image Segmentation | |
| MRFP+(Ours) Resnet50 | 44.93 | MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation | |
| NiseNet | 48.32 | What's There in the Dark | |
| MaskFormer (ResNet-50) | 55.4 | Per-Pixel Classification is Not All You Need for Semantic Segmentation |
0 of 8 row(s) selected.