Unsupervised semantic deep hashing

NEUROCOMPUTING

卷:351

Article

Jin, Sheng¹  Yao, Hongxun²  Sun, Xiaoshuai²  Zhou, Shangchen³ 

[1] Harbin Inst Technol, Comp Sci & Technol, Harbin, Heilongjiang, Peoples R China

[2] Harbin Inst Technol, Sch Comp Sci & Technol, Harbin, Heilongjiang, Peoples R China

[3] Harbin Inst Technol, Harbin, Heilongjiang, Peoples R China

关键词: Deep learning;    Unsupervised hashing;    Semantic loss;   

DOI  :  10.1016/j.neucom.2019.01.020

来源: Elsevier

【 摘 要 】

In recent years, deep hashing methods have been proved to be effective since it employs convolutional neural network to learn features and hashing codes simultaneously. However, these methods are mostly supervised. In real-world applications, it is a time-consuming and overloaded task for annotating a large number of images. In this paper, we propose a novel unsupervised deep hashing method for large-scale image retrieval. Our method, namely unsupervised semantic deep hashing (USDH), uses semantic information preserved in the CNN feature layer to guide the training of network. We enforce four criteria on hashing codes learning based on VGG-19 model: 1) preserving relevant information of feature space in hashing space; 2) minimizing quantization loss between binary-like codes and hashing codes; 3) improving the usage of each bit in hashing codes by using maximum information entropy, and 4) invariant to image rotation. Extensive experiments on CIFAR-10, NUSWIDE have demonstrated that USDH outperforms several state-of-the-art unsupervised hashing methods for image retrieval. We also conduct experiments on Oxford 17 datasets for fine-grained classification to verify its efficiency for other computer vision tasks. (C) 2019 Elsevier B.V. All rights reserved.

【 授权许可】

Free