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

概要

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 HA2SH, that leverages multiple types of labels with hierarchical structures that an ethnological museum assigns to their artifacts. We experimentally prove that HA2SH can learn to generate hashes that give a better retrieval performance. Our code is available at https://github.com/wbw520/minpaku.

論文種別
発表文献
Proc.~ACM International Conference on Multimedia Retrieval (ICMR)
Bowen Wang
Bowen Wang
特任研究員
Liangzhi Li
Liangzhi Li
招へい助教

His research interests lie in deep learning, computer vision, robotics, and medical images.

中島悠太
中島悠太
准教授

コンピュータビジョン・パターン認識などの研究。ディープニューラルネットワークなどを用いた画像・映像の認識・理解を主に、自然言語処理を援用した応用研究などに従事。