Transferable Contrastive Network for Generalized Zero-Shot Learning

Zero-shot learning (ZSL) is a challenging problem that aims to recognize the target categories without seen data, where semantic information is leveraged to transfer knowledge from some source classes. Although ZSL has made great progress in recent years, most existing approaches are easy to overfit...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiang, Huajie, Wang, Ruiping, Shan, Shiguang, Chen, Xilin
Format: Conference Proceeding
Language:English
Subjects:
Fuses
Image recognition
Robustness
Semantics
Target recognition
Task analysis
Visualization
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Zero-shot learning (ZSL) is a challenging problem that aims to recognize the target categories without seen data, where semantic information is leveraged to transfer knowledge from some source classes. Although ZSL has made great progress in recent years, most existing approaches are easy to overfit the sources classes in generalized zero-shot learning (GZSL) task, which indicates that they learn little knowledge about target classes. To tackle such problem, we propose a novel Transferable Contrastive Network (TCN) that explicitly transfers knowledge from the source classes to the target classes. It automatically contrasts one image with different classes to judge whether they are consistent or not. By exploiting the class similarities to make knowledge transfer from source images to similar target classes, our approach is more robust to recognize the target images. Experiments on five benchmark datasets show the superiority of our approach for GZSL.
ISSN:2380-7504
DOI:10.1109/ICCV.2019.00986