LAVT (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-test
Overall IoU· 2021-12-04
62.09
best: 80.54 (UniLSeg-100)
SOTA
LAVT: Language-Aware Vision Transformer for Referring Image Segmentation arXiv:2112.02244
Referring Expression SegmentationonRefCOCOg-test
Overall IoU· 2021-12-04
62.09
best: 80.54 (UniLSeg-100)
SOTA
LAVT: Language-Aware Vision Transformer for Referring Image Segmentation arXiv:2112.02244