LLaVA-v1 (w/ LoRA, w/o extra data)

Reported on 3 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 Vision3 results

Image ClassificationonColonINST-v1 (Unseen)
Accuray· 2023-04-17
72.08
best: 83.24 (ColonGPT (w/ LoRA, w/o extra data))
SOTA
Visual Instruction Tuning arXiv:2304.08485
Referring expression generationonColonINST-v1 (Unseen)
Accuray· 2023-04-17
68.11
best: 80.18 (ColonGPT (w/ LoRA, w/o extra data))
SOTA
Visual Instruction Tuning arXiv:2304.08485
Referring expression generationonColonINST-v1 (Seen)
Accuray· 2023-04-17
84.55
best: 99.96 (ColonGPT (w/ LoRA, w/o extra data))
Visual Instruction Tuning arXiv:2304.08485