Asymmetric Deep Supervised Hashing
This addresses the problem of time-consuming training in deep supervised hashing for researchers and practitioners working with large-scale databases, though it is incremental as it builds on existing deep hashing methods.
The paper tackles the inefficiency of symmetric deep supervised hashing methods for large-scale nearest neighbor search by proposing an asymmetric approach that learns a deep hash function only for query points and directly learns hash codes for database points, resulting in significantly faster training and state-of-the-art performance in real applications.
Hashing has been widely used for large-scale approximate nearest neighbor search because of its storage and search efficiency. Recent work has found that deep supervised hashing can significantly outperform non-deep supervised hashing in many applications. However, most existing deep supervised hashing methods adopt a symmetric strategy to learn one deep hash function for both query points and database (retrieval) points. The training of these symmetric deep supervised hashing methods is typically time-consuming, which makes them hard to effectively utilize the supervised information for cases with large-scale database. In this paper, we propose a novel deep supervised hashing method, called asymmetric deep supervised hashing (ADSH), for large-scale nearest neighbor search. ADSH treats the query points and database points in an asymmetric way. More specifically, ADSH learns a deep hash function only for query points, while the hash codes for database points are directly learned. The training of ADSH is much more efficient than that of traditional symmetric deep supervised hashing methods. Experiments show that ADSH can achieve state-of-the-art performance in real applications.