FG-Net

Reported on 5 benchmarks across 3 tasks · 1 paper

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

Medical2 results

Semantic SegmentationonScanNet
test mIoU· 2020-12-17
69
best: 79.8 (PTv3 ARKit LabelMaker)
FG-Net: Fast Large-Scale LiDAR Point Clouds Understanding Network Leveraging Correlated Feature Mining and Geometric-Aware Modelling arXiv:2012.09439
Semantic SegmentationonPartNet
mIOU· 2020-12-17
58.2
best: 62.1 (CSN)
FG-Net: Fast Large-Scale LiDAR Point Clouds Understanding Network Leveraging Correlated Feature Mining and Geometric-Aware Modelling arXiv:2012.09439

Audio2 results

10-shot image generationonScanNet
test mIoU· 2020-12-17
69
best: 79.8 (PTv3 ARKit LabelMaker)
FG-Net: Fast Large-Scale LiDAR Point Clouds Understanding Network Leveraging Correlated Feature Mining and Geometric-Aware Modelling arXiv:2012.09439
10-shot image generationonPartNet
mIOU· 2020-12-17
58.2
best: 62.1 (CSN)
FG-Net: Fast Large-Scale LiDAR Point Clouds Understanding Network Leveraging Correlated Feature Mining and Geometric-Aware Modelling arXiv:2012.09439

Computer Vision1 result

3D Semantic SegmentationonPartNet
mIOU· 2020-12-17
58.2
best: 62.1 (CSN)
FG-Net: Fast Large-Scale LiDAR Point Clouds Understanding Network Leveraging Correlated Feature Mining and Geometric-Aware Modelling arXiv:2012.09439