CMX (SegFormer-B4)

Reported on 4 benchmarks across 2 tasks · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical2 results

Semantic SegmentationonStanford2D3D - RGBD
mIoU· 2022-03-09
62.1
SOTA
CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers arXiv:2203.04838
Semantic SegmentationonStanford2D3D - RGBD
Pixel Accuracy· 2022-03-09
82.6
best: 82.7 (ShapeConv-101)
CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers arXiv:2203.04838

Audio2 results

10-shot image generationonStanford2D3D - RGBD
mIoU· 2022-03-09
62.1
SOTA
CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers arXiv:2203.04838
10-shot image generationonStanford2D3D - RGBD
Pixel Accuracy· 2022-03-09
82.6
best: 82.7 (ShapeConv-101)
CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers arXiv:2203.04838