BESTIE (point label, proposal-free)

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

Weakly-supervised instance segmentationonPASCAL VOC 2012 val
mAP@0.25· 2021-09-20
66.4
best: 76.8 (BBAM)
Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinement arXiv:2109.09477
Weakly-supervised instance segmentationonPASCAL VOC 2012 val
mAP@0.5· 2021-09-20
56.1
best: 63.7 (BBAM)
Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinement arXiv:2109.09477
Weakly-supervised instance segmentationonPASCAL VOC 2012 val
mAP@0.75· 2021-09-20
30.2
best: 31.8 (BBAM)
Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinement arXiv:2109.09477