short-paper

Deep Collaborative Discrete Hashing with Semantic-Invariant Structure

Authors:

Zi HuangAuthors Info & Claims

SIGIR'19: Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval

Pages 905 - 908

https://doi.org/10.1145/3331184.3331275

Published: 18 July 2019 Publication History

Abstract

Existing deep hashing approaches fail to fully explore semantic correlations and neglect the effect of linguistic context on visual attention learning, leading to inferior performance. This paper proposes a dual-stream learning framework, dubbed Deep Collaborative Discrete Hashing (DCDH), which constructs a discriminative common discrete space by collaboratively incorporating the shared and individual semantics deduced from visual features and semantic labels. Specifically, the context-aware representations are generated by employing the outer product of visual embeddings and semantic encodings. Moreover, we reconstruct the labels and introduce the focal loss to take advantage of frequent and rare concepts. The common binary code space is built on the joint learning of the visual representations attended by language, the semantic-invariant structure construction and the label distribution correction. Extensive experiments demonstrate the superiority of our method.

References

[1]

Yue Cao, Mingsheng Long, Jianmin Wang, and Shichen Liu. 2017. Deep visual-semantic quantization for efficient image retrieval. In CVPR. 1328--1337.

[2]

Yue Cao, Mingsheng Long, Jianmin Wang, Han Zhu, and Qingfu Wen. 2016. Deep quantization network for efficient image retrieval. In AAAI. 3457--3463.

Digital Library

[3]

Aristides Gionis, Piotr Indyk, Rajeev Motwani, et al. 1999. Similarity search in high dimensions via hashing. In VLDB. 518--529.

Digital Library

[4]

Yunchao Gong, Svetlana Lazebnik, Albert Gordo, and Florent Perronnin. 2013. Iterative quantization: A procrustean approach to learning binary codes for large-scale image retrieval. IEEE TPAMI, Vol. 35, 12 (2013), 2916--2929.

Digital Library

[5]

Wang-Cheng Kang, Wu-Jun Li, and Zhi-Hua Zhou. 2016. Column sampling based discrete supervised hashing. In AAAI. 1230--1236.

Digital Library

[6]

Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. ImageNet classification with deep convolutional neural networks. In NIPS. Curran Associates, Inc., 1097--1105.

Digital Library

[7]

Wu-Jun Li, Sheng Wang, and Wang-Cheng Kang. 2015. Feature learning based deep supervised hashing with pairwise labels. (2015), 1711--1717.

Digital Library

[8]

Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollár. 2017. Focal loss for dense object detection. In ICCV. 2980--2988.

[9]

Bin Liu, Yue Cao, Mingsheng Long, Jianmin Wang, and Jingdong Wang. 2018. Deep triplet quantization. ACMM (2018).

Digital Library

[10]

Wei Liu, Jun Wang, Rongrong Ji, Yu-Gang Jiang, and Shih-Fu Chang. 2012. Supervised hashing with kernels. In CVPR. 2074--2081.

Digital Library

[11]

Yadan Luo, Yang Li, Fumin Shen, Yang Yang, Peng Cui, and Zi Huang. 2018a. Collaborative learning for extremely low bit asymmetric hashing. CoRR, Vol. abs/1809.09329 (2018). arxiv: 1809.09329

[12]

Yadan Luo, Yang Yang, Fumin Shen, Zi Huang, Pan Zhou, and Heng Tao Shen. 2018b. Robust discrete code modeling for supervised hashing. Pattern Recognition, Vol. 75 (2018), 128--135.

Digital Library

[13]

Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan, Edward Yang, Zachary DeVito, Zeming Lin, Alban Desmaison, Luca Antiga, and Adam Lerer. 2017. Automatic differentiation in PyTorch. (2017).

[14]

Fumin Shen, Chunhua Shen, and Wei Liu. 2015. Supervised discrete hashing. In CVPR. 37--45.

[15]

Jingdong Wang, Ting Zhang, Nicu Sebe, Heng Tao Shen, et al. 2018. A survey on learning to hash. IEEE Trans. PAMI, Vol. 40, 4 (2018), 769--790.

[16]

Yang Yang, Yadan Luo, Weilun Chen, Fumin Shen, Jie Shao, and Heng Tao Shen. 2016. Zero-shot hashing via transferring supervised knowledge. In ACMM.

Digital Library

[17]

Peichao Zhang, Wei Zhang, Wu-Jun Li, and Minyi Guo. 2014. Supervised hashing with latent factor models. In SIGIR. 173--182.

Digital Library

[18]

Zheng Zhang, Zhihui Lai, Zi Huang, W. Wong, Guosen Xie, and Li Liu. 2019. Scalable supervised asymmetric hashing with semantic and latent factor embedding. IEEE Trans. IP, Vol. 99, 99 (2019), 1--16.

[19]

Zheng Zhang, Li Liu, Fumin Shen, Heng Tao Shen, and Shao Ling. 2018. Binary Multi-View Clustering. IEEE Trans. PAMI, Vol. 99, 99 (2018), 1--9.

[20]

Zheng Zhang, Guosen Xie, Yang Li, Sheng Li, and ZI Huang. 2019. SADIH: Semantic-Aware DIscrete Hashing. In AAAI. 12--19.

[21]

Han Zhu, Mingsheng Long, Jianmin Wang, and Yue Cao. 2016. Deep Hashing Network for Efficient Similarity Retrieval. In AAAI. 2415--2421.

Digital Library

Cited By

Fu SCao CTao FZou BLin XSun J(2023)LGWAE: Label-Guided Weighted Autoencoder Network for Flexible Targeted Attacks of Deep Hashing2023 International Joint Conference on Neural Networks (IJCNN)10.1109/IJCNN54540.2023.10191987(1-9)Online publication date: 18-Jun-2023
https://doi.org/10.1109/IJCNN54540.2023.10191987
Li LSun W(2023)Multi-Hop Correlation Preserving Hashing for Efficient Hamming Space Retrieval2023 IEEE International Conference on Data Mining (ICDM)10.1109/ICDM58522.2023.00130(1097-1102)Online publication date: 1-Dec-2023
https://doi.org/10.1109/ICDM58522.2023.00130
Zhang PLi YHuang ZXu X(2022)Aggregation-Based Graph Convolutional Hashing for Unsupervised Cross-Modal RetrievalIEEE Transactions on Multimedia10.1109/TMM.2021.305376624(466-479)Online publication date: 2022
https://doi.org/10.1109/TMM.2021.3053766
Show More Cited By

Index Terms

Deep Collaborative Discrete Hashing with Semantic-Invariant Structure
1. Information systems
  1. Information retrieval
    1. Evaluation of retrieval results
      1. Retrieval efficiency
    2. Specialized information retrieval
      1. Multimedia and multimodal retrieval
        Image search

Recommendations

A Survey on Deep Hashing Methods
Nearest neighbor search aims at obtaining the samples in the database with the smallest distances from them to the queries, which is a basic task in a range of fields, including computer vision and data mining. Hashing is one of the most widely used ...
Order preserving hashing for approximate nearest neighbor search
MM '13: Proceedings of the 21st ACM international conference on Multimedia

In this paper, we propose a novel method to learn similarity-preserving hash functions for approximate nearest neighbor (NN) search. The key idea is to learn hash functions by maximizing the alignment between the similarity orders computed from the ...
Deep Semantic Asymmetric Hashing
Artificial Neural Networks and Machine Learning – ICANN 2019: Theoretical Neural Computation
Abstract
Deep hashing, which combines binary codes learning and convolutional neural network, has achieved promising performance for highly efficient image retrieval. Asymmetric deep hashing methods, which treat query points and database points in an ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

SIGIR'19: Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval

July 2019

1512 pages

ISBN:9781450361729

DOI:10.1145/3331184

General Chairs:
Benjamin Piwowarski
CNRS - Sorbonne Universite, France
,
Max Chevalier
Universite de Toulouse, CNRS, France
,
Eric Gaussier
Universite Grenoble Alpes, CNRS, France
,
Program Chairs:
Yoelle Maarek
Amazon Research, Israel
,
Jian-Yun Nie
University of Montreal, Canada
,
Falk Scholer
RMIT University, Australia

Copyright © 2019 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGIR: ACM Special Interest Group on Information Retrieval

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 18 July 2019

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Short-paper

Funding Sources

ARC

Conference

SIGIR '19

Sponsor:

SIGIR

SIGIR '19: The 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval

July 21 - 25, 2019

Paris, France

Acceptance Rates

SIGIR'19 Paper Acceptance Rate 84 of 426 submissions, 20%;

Overall Acceptance Rate 792 of 3,983 submissions, 20%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

10
Total Citations
View Citations
324
Total Downloads

Downloads (Last 12 months)15
Downloads (Last 6 weeks)2

Reflects downloads up to 04 Oct 2024

Other Metrics

View Author Metrics

Citations

Cited By

Fu SCao CTao FZou BLin XSun J(2023)LGWAE: Label-Guided Weighted Autoencoder Network for Flexible Targeted Attacks of Deep Hashing2023 International Joint Conference on Neural Networks (IJCNN)10.1109/IJCNN54540.2023.10191987(1-9)Online publication date: 18-Jun-2023
https://doi.org/10.1109/IJCNN54540.2023.10191987
Li LSun W(2023)Multi-Hop Correlation Preserving Hashing for Efficient Hamming Space Retrieval2023 IEEE International Conference on Data Mining (ICDM)10.1109/ICDM58522.2023.00130(1097-1102)Online publication date: 1-Dec-2023
https://doi.org/10.1109/ICDM58522.2023.00130
Zhang PLi YHuang ZXu X(2022)Aggregation-Based Graph Convolutional Hashing for Unsupervised Cross-Modal RetrievalIEEE Transactions on Multimedia10.1109/TMM.2021.305376624(466-479)Online publication date: 2022
https://doi.org/10.1109/TMM.2021.3053766
Zhu LZheng CLu XCheng ZNie LZhang H(2021)Efficient Multi-modal Hashing with Online Query Adaption for Multimedia RetrievalACM Transactions on Information Systems10.1145/347718040:2(1-36)Online publication date: 27-Sep-2021
https://dl.acm.org/doi/10.1145/3477180
Zhao SChen BZhang ZLu G(2021)An Embarrassingly Simple Approach to Discrete Supervised HashingProceedings of the 3rd ACM International Conference on Multimedia in Asia10.1145/3469877.3493595(1-5)Online publication date: 1-Dec-2021
https://dl.acm.org/doi/10.1145/3469877.3493595
Wang ZZhang ZLuo YHuang ZShen H(2021)Deep Collaborative Discrete Hashing With Semantic-Invariant Structure ConstructionIEEE Transactions on Multimedia10.1109/TMM.2020.299526723(1274-1286)Online publication date: 1-Jan-2021
https://dl.acm.org/doi/10.1109/TMM.2020.2995267
Xu PHuang YYuan TXiang THospedales TSong YWang L(2021)On Learning Semantic Representations for Large-Scale Abstract SketchesIEEE Transactions on Circuits and Systems for Video Technology10.1109/TCSVT.2020.304158631:9(3366-3379)Online publication date: Sep-2021
https://doi.org/10.1109/TCSVT.2020.3041586
Zhang PLuo YHuang ZXu XSong J(2021)High-order nonlocal Hashing for unsupervised cross-modal retrievalWorld Wide Web10.1007/s11280-020-00859-y24:2(563-583)Online publication date: 27-Feb-2021
https://doi.org/10.1007/s11280-020-00859-y
Luo YHuang ZWang ZZhang ZBaktashmotlagh MWen Chen CCucchiara RHua XQi GRicci EZhang ZZimmermann R(2020)Adversarial Bipartite Graph Learning for Video Domain AdaptationProceedings of the 28th ACM International Conference on Multimedia10.1145/3394171.3413897(19-27)Online publication date: 12-Oct-2020
https://dl.acm.org/doi/10.1145/3394171.3413897
Liu LZhang ZHuang Z(2020)Flexible Discrete Multi-view Hashing with Collective Latent Feature LearningNeural Processing Letters10.1007/s11063-020-10221-yOnline publication date: 16-Mar-2020
https://doi.org/10.1007/s11063-020-10221-y

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents