GSVA-Llama2-13B

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 SegmentationongRefCOCO
cIoU· uses extra data· 2023-12-15
66.38
best: 72 (DeRIS-L)
SOTA
GSVA: Generalized Segmentation via Multimodal Large Language Models arXiv:2312.10103
Instance SegmentationongRefCOCO
gIoU· uses extra data· 2023-12-15
70.04
best: 77.67 (DeRIS-L)
SOTA
GSVA: Generalized Segmentation via Multimodal Large Language Models arXiv:2312.10103
Referring Expression SegmentationongRefCOCO
cIoU· uses extra data· 2023-12-15
66.38
best: 72 (DeRIS-L)
SOTA
GSVA: Generalized Segmentation via Multimodal Large Language Models arXiv:2312.10103
Referring Expression SegmentationongRefCOCO
gIoU· uses extra data· 2023-12-15
70.04
best: 77.67 (DeRIS-L)
SOTA
GSVA: Generalized Segmentation via Multimodal Large Language Models arXiv:2312.10103