Ghosh, S (2021) Adversarial Training of Variational Auto-encoders for Continual Zero-shot Learning(A-CZSL). In: International Joint Conference on Neural Networks, IJCNN 2021, 18 - 22 July 2021, Virtual, Shenzhen.
|
PDF
IJCNN_2021.pdf - Published Version Download (1MB) | Preview |
Abstract
Most 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). The code url is available at the arxiv paper. © 2021 IEEE.
| Item Type: | Conference Paper |
|---|---|
| Publication: | Proceedings of the International Joint Conference on Neural Networks |
| Publisher: | Institute of Electrical and Electronics Engineers Inc. |
| Additional Information: | The copyright for this article belongs to the Authors. |
| Keywords: | Neural networks; Signal encoding, Auto encoders; Catastrophic forgetting; Continual learning; Learn+; Learning models; Learning settings; Real case scenarios; Real-world; Task performance; Training process, Learning systems |
| Department/Centre: | Division of Mechanical Sciences > Aerospace Engineering(Formerly Aeronautical Engineering) |
| Date Deposited: | 16 May 2023 09:11 |
| Last Modified: | 16 May 2023 09:11 |
| URI: | https://eprints.iisc.ac.in/id/eprint/81659 |
Actions (login required)
 |
View Item |
