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 | AMES | mAP | 90.7 | — | Unverified |
| 2 | Hypergraph propagation+Community selection | mAP | 88.4 | — | Unverified |
| 3 | Token | mAP | 82.28 | — | Unverified |
| 4 | FIRe | mAP | 81.8 | — | Unverified |
| 5 | DELG+ α QE reranking + RRT reranking | mAP | 80.4 | — | Unverified |
| 6 | HOW | mAP | 79.4 | — | Unverified |
| 7 | ResNet101+ArcFace GLDv2-train-clean | mAP | 74.2 | — | Unverified |
| 8 | DELF–HQE+SP | mAP | 73.4 | — | Unverified |
| 9 | HesAff–rSIFT–HQE+SP | mAP | 71.3 | — | Unverified |
| 10 | DELF–ASMK*+SP | mAP | 67.8 | — | Unverified |