VWL-M

Reported on 6 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.

Medical3 results

Semantic SegmentationonCOCO 2014 val
mIoU· 2022-02-10
36.1
best: 56.8 (DHR (Swin-L, Mask2Former))
Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling arXiv:2202.04812
Semantic SegmentationonPASCAL VOC 2012 val
Mean IoU· 2022-02-10
70.6
best: 83.4 (SemPLeS (Swin-L))
Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling arXiv:2202.04812
Semantic SegmentationonPASCAL VOC 2012 test
Mean IoU· 2022-02-10
70.4
best: 82.9 (SemPLeS (Swin-L))
Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling arXiv:2202.04812

Audio3 results

10-shot image generationonCOCO 2014 val
mIoU· 2022-02-10
36.1
best: 56.8 (DHR (Swin-L, Mask2Former))
Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling arXiv:2202.04812
10-shot image generationonPASCAL VOC 2012 val
Mean IoU· 2022-02-10
70.6
best: 83.4 (SemPLeS (Swin-L))
Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling arXiv:2202.04812
10-shot image generationonPASCAL VOC 2012 test
Mean IoU· 2022-02-10
70.4
best: 82.9 (SemPLeS (Swin-L))
Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling arXiv:2202.04812