Image Retrieval
Image Retrieval is a fundamental and long-standing computer vision task that involves finding images similar to a given query from a large database. It is often considered a form of fine-grained, instance-level classification. The task is integral to image recognition alongside classification and cross-modal retrieval. By leveraging visual similarity and other criteria, image retrieval enables users to efficiently discover relevant images, making it a crucial tool in applications such as search and recommendation.
Extending CLIP for Category-to-image Retrieval in E-commerce
( Image credit: DELF )
Papers
Showing 1–10 of 2239 papers
All datasetsROxford (Hard)ROxford (Medium)RParis (Hard)RParis (Medium)CREPE (Compositional REPresentation Evaluation)Fashion IQFlickr30K 1K testCIRRSOPFlickr30k-CNOxf5kFlickr30k
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | InternVL-G-FT | R@1 | 85.9 | — | Unverified |
| 2 | InternVL-C-FT | R@1 | 85.2 | — | Unverified |
| 3 | CN-CLIP (ViT-L/14@336px) | R@1 | 84.4 | — | Unverified |
| 4 | R2D2 (ViT-L/14) | R@1 | 84.4 | — | Unverified |
| 5 | CN-CLIP (ViT-H/14) | R@1 | 83.8 | — | Unverified |
| 6 | CN-CLIP (ViT-L/14) | R@1 | 82.7 | — | Unverified |
| 7 | CN-CLIP (ViT-B/16) | R@1 | 79.1 | — | Unverified |
| 8 | R2D2 (ViT-B) | R@1 | 78.3 | — | Unverified |
| 9 | Wukong (ViT-L/14) | R@1 | 77.4 | — | Unverified |
| 10 | Wukong (ViT-B/32) | R@1 | 67.6 | — | Unverified |