Transductive Zero-Shot Hashing for Multilabel Image Retrieval

Hash coding has been widely used in the approximate nearest neighbor search for large-scale image retrieval. Given semantic annotations such as class labels and pairwise similarities of the training data, hashing methods can learn and generate effective and compact binary codes. While some newly int...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transaction on neural networks and learning systems Vol. 33; no. 4; pp. 1673 - 1687
Main Authors: Zou, Qin, Cao, Ling, Zhang, Zheng, Chen, Long, Wang, Song
Format: Journal Article
Language:English
Published: United States IEEE 01.04.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Annotations
Binary codes
Data models
Deep hashing
Hash functions
Image coding
Image management
Image retrieval
Labels
multilabel image
Quantization (signal)
Semantics
Training
transductive learning
Visualization
zero-shot learning
ISSN:2162-237X, 2162-2388, 2162-2388
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Hash coding has been widely used in the approximate nearest neighbor search for large-scale image retrieval. Given semantic annotations such as class labels and pairwise similarities of the training data, hashing methods can learn and generate effective and compact binary codes. While some newly introduced images may contain undefined semantic labels, which we call unseen images, zero-shot hashing (ZSH) techniques have been studied for retrieval. However, existing ZSH methods mainly focus on the retrieval of single-label images and cannot handle multilabel ones. In this article, for the first time, a novel transductive ZSH method is proposed for multilabel unseen image retrieval. In order to predict the labels of the unseen/target data, a visual-semantic bridge is built via instance-concept coherence ranking on the seen/source data. Then, pairwise similarity loss and focal quantization loss are constructed for training a hashing model using both the seen/source and unseen/target data. Extensive evaluations on three popular multilabel data sets demonstrate that the proposed hashing method achieves significantly better results than the comparison methods.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2162-237X
2162-2388
2162-2388
DOI:10.1109/TNNLS.2020.3043298