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 | Swin-T (MosaiCLIP, CC-12M) | Recall@1 (HN-Atom, UC) | 44.5 | — | Unverified |
| 2 | RN-50 (MosaiCLIP, CC-12M) | Recall@1 (HN-Atom, UC) | 44.4 | — | Unverified |
| 3 | MosaiCLIP (YFCC-FT) | Recall@1 (HN-Atom, UC) | 41.5 | — | Unverified |
| 4 | RN-50 (NegCLIP, CC-12M) | Recall@1 (HN-Atom, UC) | 41.4 | — | Unverified |
| 5 | MosaiCLIP (CC-FT) | Recall@1 (HN-Atom, UC) | 40.9 | — | Unverified |
| 6 | Swin-T (NegCLIP, CC-12M) | Recall@1 (HN-Atom, UC) | 39.6 | — | Unverified |
| 7 | CLIP (YFCC-FT) | Recall@1 (HN-Atom, UC) | 39.5 | — | Unverified |
| 8 | ViT-L-14 (LAION400M) | Recall@1 (HN-Atom + HN-Comp, SC) | 39.44 | — | Unverified |
| 9 | NegCLIP (YFCC-FT) | Recall@1 (HN-Atom, UC) | 39 | — | Unverified |
| 10 | CLIP-FT (YFCC-FT) | Recall@1 (HN-Atom, UC) | 38.3 | — | Unverified |