VLT (Darknet53)

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 SegmentationonRefCOCOg-test
Overall IoU· 2021-08-12
56.65
best: 80.54 (UniLSeg-100)
SOTA
Vision-Language Transformer and Query Generation for Referring Segmentation arXiv:2108.05565
Instance SegmentationonRefCOCOg-val
Overall IoU· 2021-08-12
52.99
best: 79.9 (MLCD-Seg-7B)
SOTA
Vision-Language Transformer and Query Generation for Referring Segmentation arXiv:2108.05565
Referring Expression SegmentationonRefCOCOg-test
Overall IoU· 2021-08-12
56.65
best: 80.54 (UniLSeg-100)
SOTA
Vision-Language Transformer and Query Generation for Referring Segmentation arXiv:2108.05565
Referring Expression SegmentationonRefCOCOg-val
Overall IoU· 2021-08-12
52.99
best: 79.9 (MLCD-Seg-7B)
SOTA
Vision-Language Transformer and Query Generation for Referring Segmentation arXiv:2108.05565