Image Retrieval by Hierarchy-aware Deep Hashing Based on Multi-task Learning


Deep hashing has been widely used to approximate nearest-neighbor search for image retrieval tasks. Most of them are trained with image-label pairs without any inter-label relationship, which may not make full use of the real-world data. This paper presents deep hashing, named HA$^2$SH, that leverages multiple types of labels with hierarchical structures that an ethnological museum assigns to their artifacts. We experimentally prove that HA$^2$SH can learn to generate hashes that give a better retrieval performance.

ACM International Conference on Multimedia Retrieval (ICMR)