RefVOS with BERT + MLM loss

Reported on 6 benchmarks across 2 tasks · 1 paper

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

Computer Vision6 results

Instance SegmentationonRefCoCo val
Overall IoU· 2020-10-01
59.45
best: 85.41 (DeRIS-L)
RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation arXiv:2010.00263
Instance SegmentationonRefCOCO+ val
Overall IoU· 2020-10-01
44.71
best: 79.4 (MLCD-Seg-7B)
RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation arXiv:2010.00263
Instance SegmentationonRefCOCO+ test B
Overall IoU· 2020-10-01
36.17
best: 75.6 (MLCD-Seg-7B)
RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation arXiv:2010.00263
Referring Expression SegmentationonRefCoCo val
Overall IoU· 2020-10-01
59.45
best: 85.41 (DeRIS-L)
RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation arXiv:2010.00263
Referring Expression SegmentationonRefCOCO+ val
Overall IoU· 2020-10-01
44.71
best: 79.4 (MLCD-Seg-7B)
RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation arXiv:2010.00263
Referring Expression SegmentationonRefCOCO+ test B
Overall IoU· 2020-10-01
36.17
best: 75.6 (MLCD-Seg-7B)
RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation arXiv:2010.00263