BLIP-2 ViT-L (fine-tuned)

Reported on 3 benchmarks across 1 task · 1 paper

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

Computer Vision3 results

Image RetrievalonCOCO (Common Objects in Context)
Recall@10· 2023-01-30
91.8
best: 98.3 (Oscar)
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models arXiv:2301.12597
Image RetrievalonCOCO (Common Objects in Context)
recall@1· 2023-01-30
66.3
best: 68.3 (BLIP-2 ViT-G (fine-tuned))
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models arXiv:2301.12597
Image RetrievalonCOCO (Common Objects in Context)
recall@5· 2023-01-30
86.5
best: 91.8 (VisualSparta)
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models arXiv:2301.12597