AMES: Asymmetric and Memory-Efficient Similarity Estimation for Instance-level Retrieval | ✓ Link | 90.7 | AMES | 2024-08-06 |
Hypergraph Propagation and Community Selection for Objects Retrieval | ✓ Link | 88.4 | Hypergraph propagation+Community selection | 2021-12-01 |
Learning Token-based Representation for Image Retrieval | ✓ Link | 82.28 | Token | 2021-12-12 |
Learning Super-Features for Image Retrieval | ✓ Link | 81.8 | FIRe | 2022-01-31 |
Instance-level Image Retrieval using Reranking Transformers | ✓ Link | 80.4 | DELG+ α QE reranking + RRT reranking | 2021-03-22 |
Learning and aggregating deep local descriptors for instance-level recognition | ✓ Link | 79.4 | HOW | 2020-07-26 |
Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval | ✓ Link | 74.2 | ResNet101+ArcFace GLDv2-train-clean | 2020-04-03 |
Large-Scale Image Retrieval with Attentive Deep Local Features | ✓ Link | 73.4 | DELF–HQE+SP | 2016-12-19 |
Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking | ✓ Link | 71.3 | HesAff–rSIFT–HQE+SP | 2018-03-29 |
Large-Scale Image Retrieval with Attentive Deep Local Features | ✓ Link | 67.8 | DELF–ASMK*+SP | 2016-12-19 |
Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking | ✓ Link | 66.3 | HesAff–rSIFT–HQE | 2018-03-29 |
Dark Side Augmentation: Generating Diverse Night Examples for Metric Learning | ✓ Link | 66.3 | HED-N-GAN | 2023-09-28 |
Fine-tuning CNN Image Retrieval with No Human Annotation | ✓ Link | 64.7 | R–GeM | 2017-11-03 |
End-to-end Learning of Deep Visual Representations for Image Retrieval | ✓ Link | 60.9 | R–R-MAC | 2016-10-25 |
Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking | ✓ Link | 60.6 | HesAff–rSIFT–ASMK*+SP | 2018-03-29 |
Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking | ✓ Link | 60.4 | HesAff–rSIFT–ASMK* | 2018-03-29 |
Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking | ✓ Link | 59.8 | HesAff–rSIFT–SMK*+SP | 2018-03-29 |
Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking | ✓ Link | 59.4 | HesAff–rSIFT–SMK* | 2018-03-29 |
Emerging Properties in Self-Supervised Vision Transformers | ✓ Link | 51.5 | Dino | 2021-04-29 |
Cross-dimensional Weighting for Aggregated Deep Convolutional Features | ✓ Link | 42.4 | R – [O] –CroW | 2015-12-13 |
Particular object retrieval with integral max-pooling of CNN activations | ✓ Link | 41.7 | R – [O] –MAC | 2015-11-18 |
Aggregating Deep Convolutional Features for Image Retrieval | ✓ Link | 39.8 | R – [O] –SPoC | 2015-10-26 |
Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking | ✓ Link | 33.9 | HesAff–rSIFT–VLAD | 2018-03-29 |