Bit-wise attention deep complementary supervised hashing for image retrieval
Bit-wise attention deep complementary supervised hashing for image retrieval
复制标题
DOI：
10.1007/s11042-021-11494-8
复制
发表时间：
2021-09
影响因子：
3.6
通讯作者：
Wing W. Y. Ng;Jiayong Li;Xing Tian;Hui Wang
中科院分区：
文献类型：
--
作者：
Wing W. Y. Ng;Jiayong Li;Xing Tian;Hui Wang
对于大规模图像检索，深度哈希是一种高效的方法。现有的深度哈希方法大多是利用卷积神经网络倒数第二个全连接层的输出作为图像的深度特征来训练单个哈希表。它们关注的是语义信息，而忽略了精细的图像结构。为了解决这个问题，本文提出了一种先进的图像哈希方法——位注意深度互补监督哈希（BADCSH）。它是一个端到端系统，以一种增强的方式训练一系列哈希表，每个哈希表都是通过纠正所有前一个哈希表引起的错误来训练的。来自网络不同层次的特征被用来训练不同的哈希表。用一个级别的特征训练的哈希表揭示了图像的语义内容，而用较低级别的特征训练的哈希表包含构成语义内容的图像的结构信息。此外，哈希层被用作网络的嵌入层来生成哈希码。为了减少哈希码冗余，最大限度地保持整体相似性，在哈希层中添加了密集关注层，以区别对待各种哈希位。最后，根据不同级别特征训练的哈希表的各自性能计算权重进行融合。在三个真实图像数据库上的实验表明，该方法在最先进的比较哈希方法中取得了最好的性能。
Deep hashing is effective and efficient for large-scale image retrieval. Most of existing deep hashing methods train a single hash table by utilizing the output of the penultimate fully-connected layer of a convolutional neural network as the deep feature of images. They concentrate on the semantic information but neglect the fine-grain image structure. To address this issue, this paper proposes an advanced image hashing method,Bit-wise Attention Deep Complementary Supervised Hashing(BADCSH). It is an end-to-end system that trains a sequence of hash tables in a boosting manner, each of which is trained by correcting errors caused by all previous ones. Features from different levels of the network are used to train different hash tables. The hash table trained with features at one level reveals a level of semantic content of the image, while the hash table trained with features at a lower level contains structural information of the image that makes up the semantic content. Moreover, the hash layer is used as an embedded layer of the network to generate hash codes. A dense attention layer is added to the hash layer to treat various hash bits differently, in order to reduce hash code redundancy and maximize overall similarity preservation. Finally, the hash tables trained on different levels of features are fused by weights computed based on their respective performance. Experiments on three real-world image databases demonstrate that the proposed method achieves the best performance among state-of-the-art comparative hashing methods.