SEARLE-XL-OTI (CLIP L/14)

Reported on 4 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 Vision4 results

Image RetrievalonCOCO (Common Objects in Context)
Actions Recall@5· 2023-03-27
31.43
best: 32.55 (iSEARLE-XL-OTI (CLIP L/14))
SOTA
Zero-Shot Composed Image Retrieval with Textual Inversion arXiv:2303.15247
Composed Image Retrieval (CoIR)onCOCO (Common Objects in Context)
Actions Recall@5· 2023-03-27
31.43
best: 32.55 (iSEARLE-XL-OTI (CLIP L/14))
SOTA
Zero-Shot Composed Image Retrieval with Textual Inversion arXiv:2303.15247
Image RetrievalonFashion IQ
(Recall@10+Recall@50)/2· 2023-03-27
37.76
best: 71.77 (DQU-CIR)
Zero-Shot Composed Image Retrieval with Textual Inversion arXiv:2303.15247
Composed Image Retrieval (CoIR)onFashion IQ
(Recall@10+Recall@50)/2· 2023-03-27
37.76
best: 60.57 (CoVR-BLIP-2)
Zero-Shot Composed Image Retrieval with Textual Inversion arXiv:2303.15247