Unsupervised Discriminative Deep Hashing With Locality and Globality Preservation

Deep hashing has greatly improved retrieval performance with the powerful learning capability of deep neural network. However, deep unsupervised hashing can hardly achieve impressive performance due to the lack of the semantic supervision. This letter proposes Unsupervised Discriminative Deep Hashin...

Full description

Saved in:
Bibliographic Details
Published in:IEEE signal processing letters 2021, Vol.28, p.518-522
Main Authors: Ni, Zhuyi, Ji, Zexuan, Lan, Long, Yuan, Yun-Hao, Shen, Xiaobo
Format: Article
Language:English
Subjects:
Adaptation models
Artificial neural networks
Clustering
Computational modeling
large-scale retrieval
Machine learning
Neural networks
Optimization
Semantics
Signal processing algorithms
Training
unsupervised deep hashing
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Deep hashing has greatly improved retrieval performance with the powerful learning capability of deep neural network. However, deep unsupervised hashing can hardly achieve impressive performance due to the lack of the semantic supervision. This letter proposes Unsupervised Discriminative Deep Hashing (UD^2H) to fulfill this gap. UD^2H is formulated to jointly perform hash code learning and clustering, and trained in an asymmetric manner to improve the efficiency. The cluster labels supervise the training of deep model to enable hash code discriminative. Based on the outputs of the deep model, UD^2H adaptively constructs a similarity graph that considers the local and global structures. Experiments on three benchmark datasets show that the proposed UD^2H outperforms the state-of-the-art unsupervised deep hashing methods.
ISSN:1070-9908
1558-2361
DOI:10.1109/LSP.2021.3059526