Deep Hashing with Semantic Hash Centers for Image Retrieval
Li Chen, Rui Liu, Yuxiang Zhou, Xudong Ma, Yong Chen, Dell Zhang

TL;DR
This paper proposes a novel deep hashing framework that uses semantic hash centers to better preserve class relationships, significantly enhancing image retrieval accuracy across multiple datasets.
Contribution
It introduces a three-stage framework, SHC, for generating semantic hash centers that encode class relationships, improving upon data-independent methods.
Findings
Achieves +7.26% MAP@100 improvement over state-of-the-art.
Achieves +7.62% MAP@1000 improvement.
Achieves +11.71% MAP@ALL improvement.
Abstract
Deep hashing is an effective approach for large-scale image retrieval. Current methods are typically classified by their supervision types: point-wise, pair-wise, and list-wise. Recent point-wise techniques (e.g., CSQ, MDS) have improved retrieval performance by pre-assigning a hash center to each class, enhancing the discriminability of hash codes across various datasets. However, these methods rely on data-independent algorithms to generate hash centers, which neglect the semantic relationships between classes and may degrade retrieval performance. This paper introduces the concept of semantic hash centers, building on the idea of traditional hash centers. We hypothesize that hash centers of semantically related classes should have closer Hamming distances, while those of unrelated classes should be more distant. To this end, we propose a three-stage framework, SHC, to generate hash…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
