BBTP

Reported on 4 benchmarks across 1 task

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

Computer Vision4 results

Instance SegmentationonCOCO test-dev
mask AP
21.1
best: 57.1 (Co-DETR)
Instance SegmentationonPASCAL VOC 2012 val
AP_50
59.1
best: 77.2 (Box2Mask-T)
Instance SegmentationonPASCAL VOC 2012 val
AP_75
21.9
best: 51.1 (Box2Mask-T)
Instance SegmentationonPASCAL VOC 2012 val
mask AP
27.5
best: 48.9 (Box2Mask-T)