CoSA (ViT-B, single-stage)

Reported on 4 benchmarks across 2 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 SegmentationonCOCO 2014 val
mIoU· 2024-02-27
51.1
best: 56.8 (DHR (Swin-L, Mask2Former))
Weakly Supervised Co-training with Swapping Assignments for Semantic Segmentation arXiv:2402.17891
Semantic SegmentationonPASCAL VOC 2012 val
Mean IoU· 2024-02-27
76.4
best: 83.4 (SemPLeS (Swin-L))
Weakly Supervised Co-training with Swapping Assignments for Semantic Segmentation arXiv:2402.17891

Audio2 results

10-shot image generationonCOCO 2014 val
mIoU· 2024-02-27
51.1
best: 56.8 (DHR (Swin-L, Mask2Former))
Weakly Supervised Co-training with Swapping Assignments for Semantic Segmentation arXiv:2402.17891
10-shot image generationonPASCAL VOC 2012 val
Mean IoU· 2024-02-27
76.4
best: 83.4 (SemPLeS (Swin-L))
Weakly Supervised Co-training with Swapping Assignments for Semantic Segmentation arXiv:2402.17891