SAT (FAT)

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 SegmentationonS3DIS Area5
mAcc· 2023-01-17
78.8
best: 81.6 (Sonata + PTv3)
SOTA
SAT: Size-Aware Transformer for 3D Point Cloud Semantic Segmentation arXiv:2301.06869
Semantic SegmentationonS3DIS Area5
mIoU· 2023-01-17
72.6
best: 76 (Sonata + PTv3)
SAT: Size-Aware Transformer for 3D Point Cloud Semantic Segmentation arXiv:2301.06869

Audio2 results

10-shot image generationonS3DIS Area5
mAcc· 2023-01-17
78.8
best: 81.6 (Sonata + PTv3)
SOTA
SAT: Size-Aware Transformer for 3D Point Cloud Semantic Segmentation arXiv:2301.06869
10-shot image generationonS3DIS Area5
mIoU· 2023-01-17
72.6
best: 76 (Sonata + PTv3)
SAT: Size-Aware Transformer for 3D Point Cloud Semantic Segmentation arXiv:2301.06869