Label-PEnet

Reported on 3 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 Vision3 results

Instance SegmentationonPASCAL VOC 2012 val
mAP@0.25· uses extra data· 2019-10-07
49.2
best: 73.4 (WeakSAM-Mask2Former (with SAM))
Label-PEnet: Sequential Label Propagation and Enhancement Networks for Weakly Supervised Instance Segmentation arXiv:1910.02624
Instance SegmentationonPASCAL VOC 2012 val
mAP@0.5· uses extra data· 2019-10-07
30.2
best: 64.4 (WeakSAM-Mask2Former (with SAM))
Label-PEnet: Sequential Label Propagation and Enhancement Networks for Weakly Supervised Instance Segmentation arXiv:1910.02624
Instance SegmentationonPASCAL VOC 2012 val
mAP@0.75· uses extra data· 2019-10-07
12.9
best: 45.3 (WeakSAM-Mask2Former (with SAM))
Label-PEnet: Sequential Label Propagation and Enhancement Networks for Weakly Supervised Instance Segmentation arXiv:1910.02624