Learning cross-domain semantic-visual relationships for transductive zero-shot learning

• Main Authors: Lv, Fengmao, Zhang, Jianyang, Yang, Guowu, Feng, Lei, Yu, Yufeng, Duan, Lixin
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: English
• Published: 2023
• Subjects: Engineering::Computer science and engineering; Transfer Learning; Domain Adaptation
• Online Access: https://hdl.handle.net/10356/172041
• Institution: Nanyang Technological University

Zero-Shot Learning (ZSL) learns models for recognizing new classes. One of the main challenges in ZSL is the domain discrepancy caused by the category inconsistency between training and testing data. Domain adaptation is the most intuitive way to address this challenge. However, existing domain adap...