EPS(DeepLabV2-ResNet101)

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 SegmentationonPASCAL VOC 2012 val
Mean IoU· uses extra data· 2021-05-19
70.9
best: 83.4 (SemPLeS (Swin-L))
Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation arXiv:2105.08965
Semantic SegmentationonPASCAL VOC 2012 test
Mean IoU· uses extra data· 2021-05-19
70.8
best: 82.9 (SemPLeS (Swin-L))
Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation arXiv:2105.08965

Audio2 results

10-shot image generationonPASCAL VOC 2012 val
Mean IoU· uses extra data· 2021-05-19
70.9
best: 83.4 (SemPLeS (Swin-L))
Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation arXiv:2105.08965
10-shot image generationonPASCAL VOC 2012 test
Mean IoU· uses extra data· 2021-05-19
70.8
best: 82.9 (SemPLeS (Swin-L))
Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation arXiv:2105.08965