Image Retrieval on FSIR-BD Compositional INQUIRE 1.0
42.7mAPCLIP-L PL
Evaluation Results
| Method | Links | |
|---|---|---|
| CLIP-L PLImage Encoder=CLIP-L, Optimization Strategy=FSIR-PL2026.03 | 42.7 | |
| CLIP-LImage Encoder=CLIP-L, Optimization Strategy=Baseline2026.03 | 34.5 | |
| BLIP-L PLImage Encoder=BLIP-L, Optimization Strategy=FSIR-PL2026.03 | 33 | |
| FSIR-CTR-Phi-3.5-CLIP-LImage Encoder=CLIP-L, Optimization Strategy=FSIR-CTR, Language Model=Phi-3.52026.03 | 33 | |
| FSIR-CTR-Phi-3.5-BLIP-LImage Encoder=BLIP-L, Optimization Strategy=FSIR-CTR, Language Model=Phi-3.52026.03 | 29.2 | |
| BLIP-LImage Encoder=BLIP-L, Optimization Strategy=Baseline2026.03 | 28.2 |