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 | Offline Diffusion | MAP | 96.2 | — | Unverified |
| 2 | CNN+IME layer | MAP | 92 | — | Unverified |
| 3 | DELF+FT+ATT+DIR+QE | MAP | 90 | — | Unverified |
| 4 | DIR+QE* | MAP | 89 | — | Unverified |
| 5 | DELF+FT+ATT | MAP | 83.8 | — | Unverified |
| 6 | IME | MAP | 83.5 | — | Unverified |
| 7 | siaMAC+QE* | MAP | 82.9 | — | Unverified |
| 8 | PCA [51] | MAP | 82.6 | — | Unverified |
| 9 | IsoMap [32] | MAP | 77.9 | — | Unverified |
| 10 | SIFT+IME layer | MAP | 62.2 | — | Unverified |