RIB (DeepLabV2-ResNet101, No Saliency)

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

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

Medical1 result

Semantic SegmentationonCOCO 2014 val
mIoU· 2021-10-13
43.8
best: 56.8 (DHR (Swin-L, Mask2Former))
SOTA
Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation arXiv:2110.06530

Audio1 result

10-shot image generationonCOCO 2014 val
mIoU· 2021-10-13
43.8
best: 56.8 (DHR (Swin-L, Mask2Former))
SOTA
Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation arXiv:2110.06530