FKAConv

Reported on 3 benchmarks across 3 tasks · 1 paper · 1 SOTA

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

Computer Vision1 result

LIDAR Semantic SegmentationonParis-Lille-3D
mIOU· 2020-04-09
0.827
SOTA
FKAConv: Feature-Kernel Alignment for Point Cloud Convolution arXiv:2004.04462

Medical1 result

Semantic SegmentationonS3DIS
Mean IoU· 2020-04-09
68.4
best: 82.3 (Sonata + PTv3)
FKAConv: Feature-Kernel Alignment for Point Cloud Convolution arXiv:2004.04462

Audio1 result

10-shot image generationonS3DIS
Mean IoU· 2020-04-09
68.4
best: 82.3 (Sonata + PTv3)
FKAConv: Feature-Kernel Alignment for Point Cloud Convolution arXiv:2004.04462