2021/04/26 by Subhankar Ghosh, Ghosh, Subhankar
Computer Science · Engineering · #Artificial intelligence #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Domain Adaptation and Few-Shot Learning #Engineering #FOS: Computer and information sciences #Forgetting #Generative grammar #Generative model #Machine learning #Multimodal Machine Learning Applications #Pattern recognition (psychology) #Shot (pellet) #Task (project management) #Zero (linguistics) #cs.CV
paper · pdf · doi:10.48550/arxiv.2104.12468
10 pages, 10 figures. arXiv admin note: text overlap with arXiv:2102.03778
arxiv created 2021/04/26 · openalex publication_date 2021/04/26 · arxiv updated 2021/04/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Continual zero-shot learning(CZSL) is a new domain to classify objects sequentially the model has not seen during training. It is more suitable than zero-shot and continual learning approaches in real-case scenarios when data may come continually with only attributes for a few classes and attributes and features for other classes. Continual learning(CL) suffers from catastrophic forgetting, and zero-shot learning(ZSL) models cannot classify objects like state-of-the-art supervised classifiers due to lack of actual data(or features) during training. This paper proposes a novel continual zero-shot learning (DVGR-CZSL) model that grows in size with each task and uses generative replay to update itself with previously learned classes to avoid forgetting. We demonstrate our hybrid model(DVGR-CZSL) outperforms the baselines and is effective on several datasets, i.e., CUB, AWA1, AWA2, and aPY. We show our method is superior in task sequentially learning with ZSL(Zero-Shot Learning). We also discuss our results on the SUN dataset.