MAFT

Reported on 3 benchmarks across 3 tasks · 1 paper · 2 SOTA

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

Computer Vision3 results

Instance SegmentationonScanNet(v2)
mAP· 2023-09-04
59.6
best: 62.2 (Relation3D)
SOTA
Mask-Attention-Free Transformer for 3D Instance Segmentation arXiv:2309.01692
3D Instance SegmentationonScanNet(v2)
mAP· 2023-09-04
59.6
best: 62.2 (Relation3D)
SOTA
Mask-Attention-Free Transformer for 3D Instance Segmentation arXiv:2309.01692
Zero-Shot Semantic SegmentationonADE20K-847
unseen mIoU
8.7