Deep Hash with Improved Dual Attention for Image Retrieval

Abstract

Recently, deep learning to hash has extensively been applied to image retrieval, due to its low storage cost and fast query speed. However, there is a defect of insufficiency and imbalance when existing hashing methods utilize the convolutional neural network (CNN) to extract image semantic features and the extracted features do not include contextual information and lack relevance among features. Furthermore, the process of the relaxation hash code can lead to an inevitable quantization error. In order to solve these problems, this paper proposes deep hash with improved dual attention for image retrieval (DHIDA), which chiefly has the following contents: (1) this paper introduces the improved dual attention mechanism (IDA) based on the ResNet18 pre-trained module to extract the feature information of the image, which consists of the position attention module and the channel attention module; (2) when calculating the spatial attention matrix and channel attention matrix, the average value and maximum value of the column of the feature map matrix are integrated in order to promote the feature representation ability and fully leverage the features of each position; and (3) to reduce quantization error, this study designs a new piecewise function to directly guide the discrete binary code. Experiments on CIFAR-10, NUS-WIDE and ImageNet-100 show that the DHIDA algorithm achieves better performance.

Deep parameter-free attention hashing for image retrieval

“…Early on, Xia et al proposed 32 to learn semantic features and hash codes separately, and there is no feedback between them. Recent supervised hashing usually designs an end-to-end learning framework to learn features and hash codes simultaneously such as 31 – 34 . On this basis, Cao et al 18 selected a activation function that make the network output is continuous hash codes.…”

“…Hence, Li et al 19 embedded channel attention and spatial attention into CNN to obtain sufficient semantic features. Yang et al 34 improved the feature map in the dual attention module and combined it with the backbone network. However, these modules can aggravate the complexity of the network model and affect the speed of training.…”

“…Therefore, each image is mapped to -dimensional vector passing through model, where is the -dimensional vector of the image. To reduce quantification loss, inspired by 34 , is processed by a piecewise function as follow: …”

“…To solve this problem, inspired by 9 , this paper has made the following improvements to : where is the Rectified Linear Unit. This paper follows the optimization policy proposed by 34 , which relax to and is set to 1.1.…”