Dynamic VAEs with Generative Replay for Continual Zero-shot Learning
This addresses a practical problem for AI systems that need to learn continuously from limited data with only attributes available for some classes, though it appears incremental as it combines existing continual learning and zero-shot learning approaches.
The paper tackles continual zero-shot learning (CZSL), where models must classify unseen objects sequentially without forgetting previous classes, by proposing DVGR-CZSL, a model that grows with each task and uses generative replay. It demonstrates effectiveness on datasets like CUB, AWA1, AWA2, and aPY, outperforming baselines.
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.