VLT (Swin-B)

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

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

Computer Vision2 results

Instance SegmentationonRefCOCOg-val
Overall IoU· 2022-10-28
63.49
best: 79.9 (MLCD-Seg-7B)
SOTA
VLT: Vision-Language Transformer and Query Generation for Referring Segmentation arXiv:2210.15871
Referring Expression SegmentationonRefCOCOg-val
Overall IoU· 2022-10-28
63.49
best: 79.9 (MLCD-Seg-7B)
SOTA
VLT: Vision-Language Transformer and Query Generation for Referring Segmentation arXiv:2210.15871