ShapeConv-101

Reported on 6 benchmarks across 2 tasks · 1 paper · 6 SOTA

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

Medical3 results

Semantic SegmentationonStanford2D3D - RGBD
Pixel Accuracy· 2021-08-24
82.7
SOTA
ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation arXiv:2108.10528
Semantic SegmentationonStanford2D3D - RGBD
mAcc· 2021-08-24
70
SOTA
ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation arXiv:2108.10528
Semantic SegmentationonStanford2D3D - RGBD
mIoU· 2021-08-24
60.6
best: 62.1 (CMX (SegFormer-B4))
SOTA
ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation arXiv:2108.10528

Audio3 results

10-shot image generationonStanford2D3D - RGBD
Pixel Accuracy· 2021-08-24
82.7
SOTA
ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation arXiv:2108.10528
10-shot image generationonStanford2D3D - RGBD
mAcc· 2021-08-24
70
SOTA
ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation arXiv:2108.10528
10-shot image generationonStanford2D3D - RGBD
mIoU· 2021-08-24
60.6
best: 62.1 (CMX (SegFormer-B4))
SOTA
ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation arXiv:2108.10528