Image Retrieval by Hierarchy-aware Deep Hashing Based on Multi-task Learning
Image Retrieval by Hierarchy-aware Deep Hashing Based on Multi-task Learning
复制标题
DOI：
10.1145/3460426.3463586
复制
发表时间：
2021-08
期刊：
影响因子：
--
通讯作者：
Bowen Wang;Liangzhi Li;Yuta Nakashima;Takehiro Yamamoto;Hiroaki Ohshima;Yoshiyuki Shoji;K. Aihara;N. Kando
中科院分区：
文献类型：
--
作者：
Bowen Wang;Liangzhi Li;Yuta Nakashima;Takehiro Yamamoto;Hiroaki Ohshima;Yoshiyuki Shoji;K. Aihara;N. Kando
深度哈希被广泛用于图像检索任务的最近邻近似搜索。它们大多是用图像-标签对进行训练，没有任何标签间的关系，可能无法充分利用真实世界的数据。本文介绍了名为HA2SH的深度哈希，它利用了民族学博物馆分配给其文物的具有层次结构的多种类型的标签。我们通过实验证明，HA2SH可以学习生成具有更好检索性能的哈希。我们的代码可在https://github.com/wbw520/minpaku上获得。
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.