模式识别与人工智能
Friday, Apr. 4, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
  2021, Vol. 34 Issue (12): 1152-1159    DOI: 10.16451/j.cnki.issn1003-6059.202112008
Researches and Applications Current Issue| Next Issue| Archive| Adv Search |
Continual Zero-Shot Learning Algorithm Based on Latent Vectors Alignment
ZHONG Xiaorong1, HU Xiao2, DING Jiayu1
1. School of Electronics and Communication Engineering, Guangzhou University, Guangzhou 510006;
2. School of Mechanical and Electrical Engineering, Guangzhou University, Guangzhou 510006

Download: PDF (709 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  Continual zero-shot learning aims to accumulate the knowledge of seen classes and utilize the knowledge for unseen classes recognition. However, catastrophic forgetting can easily occur in continual learning. Therefore, a continual zero-shot learning algorithm based on latent vectors alignment is proposed. Based on the cross and distribution aligned variational auto-encoder network, the visual latent vectors of current tasks and learned tasks are aligned to enhance the similarity of latent space of different tasks. Selective retraining is adopted to improve the discrimination ability of the current task model for learned tasks. For different tasks, the independent classifiers are trained with visual-hidden vectors of the seen classes and semantic-hidden vectors of the unseen classes to achieve zero-shot image classification. Extensive experiments on four standard datasets show that the proposed algorithm completes the continual zero-shot recognition task effectively and alleviates the catastrophic forgetting.
Key wordsContinual Zero-Shot Learning      Catastrophic Forgetting      Latent Vectors Alignment      Selective Retraining     
Received: 23 June 2021     
ZTFLH: TP 391.4  
Fund:National Natural Science Foundation of China(No.62076075)
Corresponding Authors: HU Xiao, Ph.D., professor. His research interests include machine learning, machine vision and video behavior analysis.   
About author:: ZHONG Xiaorong, master student. Her research interests include computer vision and zero shot learning.
DING Jiayu, master student. His research interests include artificial intelligence, computer vision and zero shot learning.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
ZHONG Xiaorong
HU Xiao
DING Jiayu
Cite this article:   
ZHONG Xiaorong,HU Xiao,DING Jiayu. Continual Zero-Shot Learning Algorithm Based on Latent Vectors Alignment[J]. , 2021, 34(12): 1152-1159.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202112008      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2021/V34/I12/1152
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn