Hierarchical Deep Hashing for Fast Large Scale Image Retrieval

Zhang, Yongfei; Cheng, Peng; Zhang, Jingtao; Liu, Xianglong; Pu, Shiliang; Chen, Changhuai

doi:10.1109/icpr48806.2021.9412826

Cited by 2 publications

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The binary cross entropy loss is employed to minimize the distance within the class and maximize the distance between the classes. To reduce the retrieval time and improve the retrieval speed, Zhang et al [37] use tree structures to generate the deep hash code and prune the irrelevant branches to reduce the retrieval time.…”

Section: Related Workmentioning

confidence: 99%

Deep Hash with Improved Dual Attention for Image Retrieval

et al. 2021

View full text Add to dashboard Cite

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.

show abstract

Section: Related Workmentioning

confidence: 99%