Adversarial Training of Variational Auto-encoders for Continual Zero-shot Learning(A-CZSL)
This work addresses catastrophic forgetting in continual learning for zero-shot learning scenarios, which is a critical problem for real-world applications with limited memory.
This paper proposes a continual zero-shot learning model, A-CZSL, to address catastrophic forgetting in ANNs without storing all previous data. The model learns sequentially and distinguishes unseen classes, outperforming baselines on datasets like CUB, AWA1, AWA2, and aPY in both ZSL and GZSL settings.
Most of the existing artificial neural networks(ANNs) fail to learn continually due to catastrophic forgetting, while humans can do the same by maintaining previous tasks' performances. Although storing all the previous data can alleviate the problem, it takes a large memory, infeasible in real-world utilization. We propose a continual zero-shot learning model(A-CZSL) that is more suitable in real-case scenarios to address the issue that can learn sequentially and distinguish classes the model has not seen during training. Further, to enhance the reliability, we develop A-CZSL for a single head continual learning setting where task identity is revealed during the training process but not during the testing. We present a hybrid network that consists of a shared VAE module to hold information of all tasks and task-specific private VAE modules for each task. The model's size grows with each task to prevent catastrophic forgetting of task-specific skills, and it includes a replay approach to preserve shared skills. We demonstrate our hybrid model outperforms the baselines and is effective on several datasets, i.e., CUB, AWA1, AWA2, and aPY. We show our method is superior in class sequentially learning with ZSL(Zero-Shot Learning) and GZSL(Generalized Zero-Shot Learning).