Jiang Zhukai, Lian Zhichao, Wang Jinping
School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China.
Front Neurorobot. 2021 Oct 18;15:728161. doi: 10.3389/fnbot.2021.728161. eCollection 2021.
In recent years, learning-based hashing techniques have proven to be efficient for large-scale image retrieval. However, since most of the hash codes learned by deep hashing methods contain repetitive and correlated information, there are some limitations. In this paper, we propose a Dual Attention Triplet Hashing Network (DATH). DATH is implemented with two-stream ConvNet architecture. Specifically, the first neural network focuses on the spatial semantic relevance, and the second neural network focuses on the channel semantic correlation. These two neural networks are incorporated to create an end-to-end trainable framework. At the same time, in order to make better use of label information, DATH combines triplet likelihood loss and classification loss to optimize the network. Experimental results show that DATH has achieved the state-of-the-art performance on benchmark datasets.
近年来，基于学习的哈希技术已被证明在大规模图像检索中是有效的。然而，由于深度哈希方法学习到的大多数哈希码都包含重复和相关信息，因此存在一些局限性。在本文中，我们提出了一种双注意力三元组哈希网络（DATH）。DATH采用双流卷积神经网络架构实现。具体来说，第一个神经网络专注于空间语义相关性，第二个神经网络专注于通道语义相关性。这两个神经网络被合并以创建一个端到端可训练的框架。同时，为了更好地利用标签信息，DATH结合三元组似然损失和分类损失来优化网络。实验结果表明，DATH在基准数据集上取得了领先的性能。
