IRGen: Generative Modeling for Image Retrieval
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910539322490880 |
|---|---|
| author | Zhang, Yidan Zhang, Ting Chen, Dong Wang, Yujing Chen, Qi Xie, Xing Sun, Hao Deng, Weiwei Zhang, Qi Yang, Fan Yang, Mao Liao, Qingmin Wang, Jingdong Guo, Baining |
| author_facet | Zhang, Yidan Zhang, Ting Chen, Dong Wang, Yujing Chen, Qi Xie, Xing Sun, Hao Deng, Weiwei Zhang, Qi Yang, Fan Yang, Mao Liao, Qingmin Wang, Jingdong Guo, Baining |
| contents | While generative modeling has become prevalent across numerous research fields, its integration into the realm of image retrieval remains largely unexplored and underjustified. In this paper, we present a novel methodology, reframing image retrieval as a variant of generative modeling and employing a sequence-to-sequence model. This approach is harmoniously aligned with the current trend towards unification in research, presenting a cohesive framework that allows for end-to-end differentiable searching. This, in turn, facilitates superior performance via direct optimization techniques. The development of our model, dubbed IRGen, addresses the critical technical challenge of converting an image into a concise sequence of semantic units, which is pivotal for enabling efficient and effective search. Extensive experiments demonstrate that our model achieves state-of-the-art performance on three widely-used image retrieval benchmarks as well as two million-scale datasets, yielding significant improvement compared to prior competitive retrieval methods. In addition, the notable surge in precision scores facilitated by generative modeling presents the potential to bypass the reranking phase, which is traditionally indispensable in practical retrieval workflows. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2303_10126 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | IRGen: Generative Modeling for Image Retrieval Zhang, Yidan Zhang, Ting Chen, Dong Wang, Yujing Chen, Qi Xie, Xing Sun, Hao Deng, Weiwei Zhang, Qi Yang, Fan Yang, Mao Liao, Qingmin Wang, Jingdong Guo, Baining Computer Vision and Pattern Recognition While generative modeling has become prevalent across numerous research fields, its integration into the realm of image retrieval remains largely unexplored and underjustified. In this paper, we present a novel methodology, reframing image retrieval as a variant of generative modeling and employing a sequence-to-sequence model. This approach is harmoniously aligned with the current trend towards unification in research, presenting a cohesive framework that allows for end-to-end differentiable searching. This, in turn, facilitates superior performance via direct optimization techniques. The development of our model, dubbed IRGen, addresses the critical technical challenge of converting an image into a concise sequence of semantic units, which is pivotal for enabling efficient and effective search. Extensive experiments demonstrate that our model achieves state-of-the-art performance on three widely-used image retrieval benchmarks as well as two million-scale datasets, yielding significant improvement compared to prior competitive retrieval methods. In addition, the notable surge in precision scores facilitated by generative modeling presents the potential to bypass the reranking phase, which is traditionally indispensable in practical retrieval workflows. |
| title | IRGen: Generative Modeling for Image Retrieval |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2303.10126 |