Context-I2W (CLIP L/14)

Reported on 4 benchmarks across 2 tasks · 1 paper

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

Computer Vision4 results

Image RetrievalonFashion IQ
(Recall@10+Recall@50)/2· 2023-09-28
38.35
best: 71.77 (DQU-CIR)
Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image Retrieval arXiv:2309.16137
Image RetrievalonCIRR
R@5· 2023-09-28
55.1
best: 81.08 (CoVR-BLIP-2)
Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image Retrieval arXiv:2309.16137
Composed Image Retrieval (CoIR)onFashion IQ
(Recall@10+Recall@50)/2· 2023-09-28
38.35
best: 60.57 (CoVR-BLIP-2)
Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image Retrieval arXiv:2309.16137
Composed Image Retrieval (CoIR)onCIRR
R@5· 2023-09-28
55.1
best: 81.08 (CoVR-BLIP-2)
Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image Retrieval arXiv:2309.16137