标题:Supervised deep quantization for efficient image search
作者:Yang, Dongbao ;Xie, Hongtao ;Yin, Jian ;Liu, Yizhi ;Yan, Chenggang
通讯作者:Yin, Jian
作者机构:[Yang, Dongbao ;Yin, Jian ] School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, China;[Liu, Yizhi ] School of C 更多
会议名称:2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017
会议日期:July 10, 2017 - July 14, 2017
来源:2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017
出版年:2017
页码:525-530
DOI:10.1109/ICMEW.2017.8026290
摘要:Due to the efficiency of compact binary codes in approximate nearest neighbor search for large-scale image retrieval, hashing techniques have received increasing attentions. For most existing hash methods, the suboptimal binary codes are generated, as the hand-crafted feature representation is not optimally compatible with the binary codes. In this paper, we propose a one-stage supervised hashing method to learn high-quality binary codes. We implement a deep Convolutional Neural Network and enforce the learned codes to meet the following criterions: (a) similar images should be encoded into similar binary codes, and vice versa; (b) the binary codes should be evenly distributed; (c) the loss of quantization should be minimized. Experimental comparisons between our method and state-of-the-art algorithms are conducted on CIFAR-10 and NUS-WIDE datasets, and the MAP of our method reaches to 87.67% and 77.48% with 48-bit respectively. It shows that our method can obviously improve the search accuracy.
© 2017 IEEE.
收录类别:EI
资源类型:会议论文
TOP