SeqTR

Reported on 4 benchmarks across 2 tasks · 1 paper · 4 SOTA

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

Computer Vision4 results

Instance SegmentationonRefCOCO testA
Overall IoU· 2022-03-30
69.79
best: 86.49 (DeRIS-L)
SOTA
SeqTR: A Simple yet Universal Network for Visual Grounding arXiv:2203.16265
Instance SegmentationonRefCOCO testB
Overall IoU· 2022-03-30
64.12
best: 83.4 (HyperSeg)
SOTA
SeqTR: A Simple yet Universal Network for Visual Grounding arXiv:2203.16265
Referring Expression SegmentationonRefCOCO testA
Overall IoU· 2022-03-30
69.79
best: 86.49 (DeRIS-L)
SOTA
SeqTR: A Simple yet Universal Network for Visual Grounding arXiv:2203.16265
Referring Expression SegmentationonRefCOCO testB
Overall IoU· 2022-03-30
64.12
best: 83.4 (HyperSeg)
SOTA
SeqTR: A Simple yet Universal Network for Visual Grounding arXiv:2203.16265