OPT OpenIR  > 光学影像学习与分析中心
Deep Binary Reconstruction for Cross-Modal Hashing
Hu, Di1; Nie, Feiping1; Li, Xuelong2,3,4
Contribution Rank4

To satisfy the huge storage space and organization capacity requirements in addressing big multimodal data, hashing techniques have been widely employed to learn binary representations in cross-modal retrieval tasks. However, optimizing the hashing objective under the necessary binary constraint is truly a difficult problem. A common strategy is to relax the constraint and perform individual binarizations over the learned real-valued representations. In this paper, in contrast to conventional two-stage methods, we propose to directly learn the binary codes, where the model can be easily optimized by a standard gradient descent optimizer. However, before that, we present a theoretical guarantee of the effectiveness of the multimodal network in preserving the inter-and intra-modal consistencies. Based on this guarantee, a novel multimodal deep binary reconstruction model is proposed, which can be trained to simultaneously model the correlation across modalities and learn the binary hashing codes. To generate binary codes and to avoid the tiny gradient problem, a novel activation function first scales the input activations to suitable scopes and, then, feeds them to the tanh function to build the hashing layer. Such a composite function is named adaptive tanh. Both linear and nonlinear scaling methods are proposed and shown to generate efficient codes after training the network. Extensive ablation studies and comparison experiments are conducted for the image2text and text2image retrieval tasks; the method is found to outperform several state-of-the-art deep-learning methods with respect to different evaluation metrics.

KeywordCross-modal hashing binary reconstruction
Indexed BySCI
WOS IDWOS:000462413700013
Citation statistics
Document Type期刊论文
Corresponding AuthorHu, Di
Affiliation1.Northwestern Polytech Univ, Sch Comp Sci & Engn, Xian 710072, Shaanxi, Peoples R China
2.Northwestern Polytech Univ, Sch Comp Sci, Xian 710072, Shaanxi, Peoples R China
3.Northwestern Polytech Univ, Ctr OPT IMagery Anal & Learning OPTIMAL, Xian 710072, Shaanxi, Peoples R China
4.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Xian 710119, Shaanxi, Peoples R China
Recommended Citation
GB/T 7714
Hu, Di,Nie, Feiping,Li, Xuelong. Deep Binary Reconstruction for Cross-Modal Hashing[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2019,21(4):973-985.
APA Hu, Di,Nie, Feiping,&Li, Xuelong.(2019).Deep Binary Reconstruction for Cross-Modal Hashing.IEEE TRANSACTIONS ON MULTIMEDIA,21(4),973-985.
MLA Hu, Di,et al."Deep Binary Reconstruction for Cross-Modal Hashing".IEEE TRANSACTIONS ON MULTIMEDIA 21.4(2019):973-985.
Files in This Item:
File Name/Size DocType Version Access License
Deep Binary Reconstr(1371KB)期刊论文出版稿限制开放CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Hu, Di]'s Articles
[Nie, Feiping]'s Articles
[Li, Xuelong]'s Articles
Baidu academic
Similar articles in Baidu academic
[Hu, Di]'s Articles
[Nie, Feiping]'s Articles
[Li, Xuelong]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Hu, Di]'s Articles
[Nie, Feiping]'s Articles
[Li, Xuelong]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.