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 21–30 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 | SuperGlobal | mAP | 80.2 | — | Unverified |
| 2 | AMES | mAP | 80 | — | Unverified |
| 3 | Hypergraph propagation+community selection | mAP | 73 | — | Unverified |
| 4 | Token | mAP | 66.57 | — | Unverified |
| 5 | DELG+ α QE reranking+ RRT reranking | mAP | 64 | — | Unverified |
| 6 | FIRe | mAP | 61.2 | — | Unverified |
| 7 | HOW | mAP | 56.9 | — | Unverified |
| 8 | ResNet101+ArcFace GLDv2-train-clean | mAP | 51.6 | — | Unverified |
| 9 | DELF–HQE+SP | mAP | 50.3 | — | Unverified |
| 10 | HesAff–rSIFT–HQE+SP | mAP | 49.7 | — | Unverified |
| # | 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 |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | AMES | mAP | 89.7 | — | Unverified |
| 2 | SuperGlobal | mAP | 86.7 | — | Unverified |
| 3 | Hypergraph propagation | mAP | 83.3 | — | Unverified |
| 4 | Token | mAP | 78.56 | — | Unverified |
| 5 | DELG+ α QE reranking + RRT reranking | mAP | 77.7 | — | Unverified |
| 6 | ResNet101+ArcFace GLDv2-train-clean | mAP | 70.3 | — | Unverified |
| 7 | FIRe | mAP | 70 | — | Unverified |
| 8 | DELF–HQE+SP | mAP | 69.3 | — | Unverified |
| 9 | HOW | mAP | 62.4 | — | Unverified |
| 10 | R–R-MAC | mAP | 59.4 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | AMES | mAP | 94.9 | — | Unverified |
| 2 | Hypergraph propagation | mAP | 92.6 | — | Unverified |
| 3 | Token | mAP | 89.34 | — | Unverified |
| 4 | DELG+ α QE reranking + RRT reranking | mAP | 88.5 | — | Unverified |
| 5 | FIRe | mAP | 85.3 | — | Unverified |
| 6 | ResNet101+ArcFace GLDv2-train-clean | mAP | 84.9 | — | Unverified |
| 7 | DELF–HQE+SP | mAP | 84 | — | Unverified |
| 8 | HOW | mAP | 81.6 | — | Unverified |
| 9 | R–R-MAC | mAP | 78.9 | — | Unverified |
| 10 | R–GeM | mAP | 77.2 | — | Unverified |
| # | 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 |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | DQU-CIR | (Recall@10+Recall@50)/2 | 71.77 | — | Unverified |
| 2 | TMCIR | (Recall@10+Recall@50)/2 | 66.56 | — | Unverified |
| 3 | SPN4CIR (SPRC) | (Recall@10+Recall@50)/2 | 66.41 | — | Unverified |
| 4 | SPRC | (Recall@10+Recall@50)/2 | 64.85 | — | Unverified |
| 5 | Candidate Set Re-ranking | (Recall@10+Recall@50)/2 | 62.15 | — | Unverified |
| 6 | RUTIR (BLIP B/16) | (Recall@10+Recall@50)/2 | 61.32 | — | Unverified |
| 7 | CASE | (Recall@10+Recall@50)/2 | 59.73 | — | Unverified |
| 8 | CaLa | (Recall@10+Recall@50)/2 | 57.96 | — | Unverified |
| 9 | BLIP4CIR+Bi | (Recall@10+Recall@50)/2 | 55.4 | — | Unverified |
| 10 | CLIP4Cir (v3) | (Recall@10+Recall@50)/2 | 55.36 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | X-VLM (base) | R@1 | 86.9 | — | Unverified |
| 2 | RCAR | R@1 | 62.6 | — | Unverified |
| 3 | SGRAF | R@1 | 58.5 | — | Unverified |
| 4 | VisualSparta | R@1 | 57.4 | — | Unverified |
| 5 | LGSGM | R@1 | 57.4 | — | Unverified |
| 6 | TERAN MrSw | R@1 | 56.5 | — | Unverified |
| 7 | TERAN Symm. | R@1 | 55.7 | — | Unverified |
| 8 | VSRN | R@1 | 54.7 | — | Unverified |
| 9 | CAMP | R@1 | 51.5 | — | Unverified |
| 10 | SCAN i-t | R@1 | 44 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | TMCIR | (Recall@5+Recall_subset@1)/2 | 83.46 | — | Unverified |
| 2 | SPN4CIR (SPRC) | (Recall@5+Recall_subset@1)/2 | 82.69 | — | Unverified |
| 3 | SPRC2 | (Recall@5+Recall_subset@1)/2 | 82.66 | — | Unverified |
| 4 | SPRC | (Recall@5+Recall_subset@1)/2 | 81.39 | — | Unverified |
| 5 | Candidate Set Re-ranking | (Recall@5+Recall_subset@1)/2 | 80.9 | — | Unverified |
| 6 | CaLa | (Recall@5+Recall_subset@1)/2 | 78.74 | — | Unverified |
| 7 | CASE (Pre-trained on LaSCo.Ca) | (Recall@5+Recall_subset@1)/2 | 78.25 | — | Unverified |
| 8 | CASE | (Recall@5+Recall_subset@1)/2 | 77.5 | — | Unverified |
| 9 | VISTA (base) | (Recall@5+Recall_subset@1)/2 | 75.9 | — | Unverified |
| 10 | MMRet-MLLM | (Recall@5+Recall_subset@1)/2 | 75.7 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Unicom+ViT-L@336px | R@1 | 91.2 | — | Unverified |
| 2 | ROADMAP (DeiT-B) | R@1 | 86 | — | Unverified |
| 3 | CGD (SG/GS) | R@1 | 84.2 | — | Unverified |
| 4 | ROADMAP (ResNet-50) | R@1 | 83.1 | — | Unverified |
| 5 | ProxyNCA++ | R@1 | 81.4 | — | Unverified |
| 6 | PNP Loss | R@1 | 81.1 | — | Unverified |
| 7 | Cross-Batch Memory | R@1 | 80.6 | — | Unverified |
| 8 | Smooth-AP | R@1 | 80.1 | — | Unverified |
| 9 | NormSoftmax2048 (ResNet-50) | R@1 | 79.5 | — | Unverified |
| 10 | EPSHN512 | R@1 | 78.3 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | InternVL-G-FT | R@1 | 85.9 | — | Unverified |
| 2 | InternVL-C-FT | R@1 | 85.2 | — | Unverified |
| 3 | R2D2 (ViT-L/14) | R@1 | 84.4 | — | Unverified |
| 4 | CN-CLIP (ViT-L/14@336px) | 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 |
| # | 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 |