English

Contextual Similarity Aggregation with Self-attention for Visual Re-ranking

Computer Vision and Pattern Recognition 2021-10-27 v1

Abstract

In content-based image retrieval, the first-round retrieval result by simple visual feature comparison may be unsatisfactory, which can be refined by visual re-ranking techniques. In image retrieval, it is observed that the contextual similarity among the top-ranked images is an important clue to distinguish the semantic relevance. Inspired by this observation, in this paper, we propose a visual re-ranking method by contextual similarity aggregation with self-attention. In our approach, for each image in the top-K ranking list, we represent it into an affinity feature vector by comparing it with a set of anchor images. Then, the affinity features of the top-K images are refined by aggregating the contextual information with a transformer encoder. Finally, the affinity features are used to recalculate the similarity scores between the query and the top-K images for re-ranking of the latter. To further improve the robustness of our re-ranking model and enhance the performance of our method, a new data augmentation scheme is designed. Since our re-ranking model is not directly involved with the visual feature used in the initial retrieval, it is ready to be applied to retrieval result lists obtained from various retrieval algorithms. We conduct comprehensive experiments on four benchmark datasets to demonstrate the generality and effectiveness of our proposed visual re-ranking method.

Keywords

Cite

@article{arxiv.2110.13430,
  title  = {Contextual Similarity Aggregation with Self-attention for Visual Re-ranking},
  author = {Jianbo Ouyang and Hui Wu and Min Wang and Wengang Zhou and Houqiang Li},
  journal= {arXiv preprint arXiv:2110.13430},
  year   = {2021}
}

Comments

Accepted to NeurIPS, 2021

R2 v1 2026-06-24T07:11:14.495Z