Swin-S + Mask R-CNN

Reported on 2 benchmarks across 1 task · 1 paper

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

Computer Vision2 results

Instance SegmentationonOccluded COCO
Mean Recall· 2021-03-25
61.14
best: 63.64 (Swin-B + Cascade Mask R-CNN (tri-layer modelling))
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows arXiv:2103.14030
Instance SegmentationonSeparated COCO
Mean Recall· 2021-03-25
33.67
best: 36.88 (Swin-B + Cascade Mask R-CNN (tri-layer modelling))
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows arXiv:2103.14030