GSVA-Vicuna-7B-v1.1

Reported on 4 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 Vision4 results

Instance SegmentationongRefCOCO
cIoU· uses extra data· 2023-12-15
63.29
best: 72 (DeRIS-L)
GSVA: Generalized Segmentation via Multimodal Large Language Models arXiv:2312.10103
Instance SegmentationongRefCOCO
gIoU· uses extra data· 2023-12-15
66.47
best: 77.67 (DeRIS-L)
GSVA: Generalized Segmentation via Multimodal Large Language Models arXiv:2312.10103
Referring Expression SegmentationongRefCOCO
cIoU· uses extra data· 2023-12-15
63.29
best: 72 (DeRIS-L)
GSVA: Generalized Segmentation via Multimodal Large Language Models arXiv:2312.10103
Referring Expression SegmentationongRefCOCO
gIoU· uses extra data· 2023-12-15
66.47
best: 77.67 (DeRIS-L)
GSVA: Generalized Segmentation via Multimodal Large Language Models arXiv:2312.10103