IDHashGAN: Deep Hashing With Generative Adversarial Nets for Incomplete Data Retrieval
- 1 January 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 24 (99), 534-545
- https://doi.org/10.1109/TMM.2021.3054503
Abstract
Benefiting from low storage costs and high retrieval efficiency, hash learning has been a widely adopted technology for approximating nearest neighbor in large-scale data retrieval. Deep learning to hash greatly improves image retrieval performance by integrating feature learning and hash coding into an end-to-end framework. However, subject to application scope, most existing deep hashing methods only apply to retrieval of complete data and have undesirable results when retrieving incomplete but valuable data. In this paper we propose IDHashGAN, a novel deep hashing model with generative adversarial networks to retrieve incomplete data, in which feature restoration, feature learning and hash coding are integrated into an unified end-to-end framework. The proposed model consists of four key components: (1) reconstructive and generative loss are used to generate continuous feature of incomplete data in generative network; (2) supervised manifold similarity is proposed to improve retrieval accuracy and obtain good user acceptance; (3) adversarial and classified loss are designed to distinguish authenticity and similarity in discriminative network; and (4) encoding and quantization loss are adopted to preserve similarity and control hash quality. Extensive experiments on benchmark datasets show that IDHashGAN is competitive on complete dataset and yields substantial boosts of 70% on incomplete datasets compared to state-of-the-art hashing methods.Funding Information
- National Natural Science Foundation of China (61672120, 62076044)
- Natural Science Foundation of Chongqing, China (cstc2019jcyj-zdxm0011)
- Chongqing University of Posts and Telecommunications (BYJS201812)
- Doctoral Research Innovation Project of Chongqing (CYB19173)
This publication has 32 references indexed in Scilit:
- Deep Supervised Hashing with Triplet LabelsPublished by Springer Science and Business Media LLC ,2017
- Deep Supervised Hashing for Fast Image RetrievalPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Bit-Scalable Deep Hashing With Regularized Similarity Learning for Image Retrieval and Person Re-IdentificationIEEE Transactions on Image Processing, 2015
- Deep learning of binary hash codes for fast image retrievalPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Simultaneous feature learning and hash coding with deep neural networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Deep hashing for compact binary codes learningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Supervised Discrete HashingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Asymmetric Cyclical Hashing for Large Scale Image RetrievalIEEE Transactions on Multimedia, 2015
- Graph Cuts for Supervised Binary CodingLecture Notes in Computer Science, 2014
- Semi-Supervised Hashing for Large-Scale SearchIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012