LocVLM-L

Reported on 6 benchmarks across 2 tasks · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing6 results

Visual Question AnsweringonGQA
Accuracy· 2024-04-11
50.2
SOTA
Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs arXiv:2404.07449
Visual Question Answering (VQA)onVQA v2 test-dev
Accuracy· 2024-04-11
56.2
best: 84.3 (PaLI)
Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs arXiv:2404.07449
Visual Question Answering (VQA)onGQA
Accuracy· 2024-04-11
50.2
best: 77 (PEVL+)
Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs arXiv:2404.07449
Visual Question Answering (VQA)onVQA v2 val
Accuracy· 2024-04-11
55.9
best: 82.19 (BLIP-2 ViT-G OPT 6.7B (fine-tuned))
Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs arXiv:2404.07449
Visual Question AnsweringonVQA v2 test-dev
Accuracy· 2024-04-11
56.2
best: 82.3 (BLIP-2 ViT-G OPT 6.7B (fine-tuned))
Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs arXiv:2404.07449
Visual Question AnsweringonVQA v2 val
Accuracy· 2024-04-11
55.9
best: 82.19 (BLIP-2 ViT-G OPT 6.7B (fine-tuned))
Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs arXiv:2404.07449