BBTP (ResNet-101)

Reported on 6 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 Vision6 results

Weakly-supervised instance segmentationonCOCO 2017 val
AP· 2021-10-03
21.1
best: 31.4 (DiscoBox (ResNet-50))
Bounding Box Tightness Prior for Weakly Supervised Image Segmentation arXiv:2110.00934
Weakly-supervised instance segmentationonCOCO 2017 val
AP@50· 2021-10-03
45.5
best: 52.6 (DiscoBox (ResNet-50))
Bounding Box Tightness Prior for Weakly Supervised Image Segmentation arXiv:2110.00934
Weakly-supervised instance segmentationonCOCO 2017 val
AP@75· 2021-10-03
17.2
best: 32.2 (DiscoBox (ResNet-50))
Bounding Box Tightness Prior for Weakly Supervised Image Segmentation arXiv:2110.00934
Weakly-supervised instance segmentationonCOCO 2017 val
AP@L· 2021-10-03
29.8
best: 50.1 (DiscoBox (ResNet-50))
Bounding Box Tightness Prior for Weakly Supervised Image Segmentation arXiv:2110.00934
Weakly-supervised instance segmentationonCOCO 2017 val
AP@M· 2021-10-03
22
best: 33.8 (DiscoBox (ResNet-50))
Bounding Box Tightness Prior for Weakly Supervised Image Segmentation arXiv:2110.00934
Weakly-supervised instance segmentationonCOCO 2017 val
AP@S· 2021-10-03
11.2
best: 11.5 (DiscoBox (ResNet-50))
Bounding Box Tightness Prior for Weakly Supervised Image Segmentation arXiv:2110.00934