LOCORE: Image Re-ranking with Long-Context Sequence Modeling
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909555413221376 |
|---|---|
| author | Xiao, Zilin Suma, Pavel Sachdeva, Ayush Wang, Hao-Jen Kordopatis-Zilos, Giorgos Tolias, Giorgos Ordonez, Vicente |
| author_facet | Xiao, Zilin Suma, Pavel Sachdeva, Ayush Wang, Hao-Jen Kordopatis-Zilos, Giorgos Tolias, Giorgos Ordonez, Vicente |
| contents | We introduce LOCORE, Long-Context Re-ranker, a model that takes as input local descriptors corresponding to an image query and a list of gallery images and outputs similarity scores between the query and each gallery image. This model is used for image retrieval, where typically a first ranking is performed with an efficient similarity measure, and then a shortlist of top-ranked images is re-ranked based on a more fine-grained similarity measure. Compared to existing methods that perform pair-wise similarity estimation with local descriptors or list-wise re-ranking with global descriptors, LOCORE is the first method to perform list-wise re-ranking with local descriptors. To achieve this, we leverage efficient long-context sequence models to effectively capture the dependencies between query and gallery images at the local-descriptor level. During testing, we process long shortlists with a sliding window strategy that is tailored to overcome the context size limitations of sequence models. Our approach achieves superior performance compared with other re-rankers on established image retrieval benchmarks of landmarks (ROxf and RPar), products (SOP), fashion items (In-Shop), and bird species (CUB-200) while having comparable latency to the pair-wise local descriptor re-rankers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_21772 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LOCORE: Image Re-ranking with Long-Context Sequence Modeling Xiao, Zilin Suma, Pavel Sachdeva, Ayush Wang, Hao-Jen Kordopatis-Zilos, Giorgos Tolias, Giorgos Ordonez, Vicente Computer Vision and Pattern Recognition We introduce LOCORE, Long-Context Re-ranker, a model that takes as input local descriptors corresponding to an image query and a list of gallery images and outputs similarity scores between the query and each gallery image. This model is used for image retrieval, where typically a first ranking is performed with an efficient similarity measure, and then a shortlist of top-ranked images is re-ranked based on a more fine-grained similarity measure. Compared to existing methods that perform pair-wise similarity estimation with local descriptors or list-wise re-ranking with global descriptors, LOCORE is the first method to perform list-wise re-ranking with local descriptors. To achieve this, we leverage efficient long-context sequence models to effectively capture the dependencies between query and gallery images at the local-descriptor level. During testing, we process long shortlists with a sliding window strategy that is tailored to overcome the context size limitations of sequence models. Our approach achieves superior performance compared with other re-rankers on established image retrieval benchmarks of landmarks (ROxf and RPar), products (SOP), fashion items (In-Shop), and bird species (CUB-200) while having comparable latency to the pair-wise local descriptor re-rankers. |
| title | LOCORE: Image Re-ranking with Long-Context Sequence Modeling |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.21772 |