Gautam, C and Parameswaran, S and Mishra, A and Sundaram, S (2022) Tf-GCZSL: Task-free generalized continual zero-shot learning. In: Neural Networks, 155 . pp. 487-497.
|
PDF
Neural Networks_155_487-497_2022.pdf - Published Version Download (2MB) | Preview |
Abstract
Learning continually from a stream of training data or tasks with an ability to learn the unseen classes using a zero-shot learning framework is gaining attention in the literature. It is referred to as continual zero-shot learning (CZSL). Existing CZSL requires clear task-boundary information during training which is not practically feasible. This paper proposes a task-free generalized CZSL (Tf-GCZSL) method with short-term/long-term memory to overcome the requirement of task-boundary in training. A variational autoencoder (VAE) handles the fundamental ZSL tasks. The short-term and long-term memory help to overcome the condition of the task boundary in the CZSL framework. Further, the proposed Tf-GCZSL method combines the concept of experience replay with dark knowledge distillation and regularization to overcome the catastrophic forgetting issues in a continual learning framework. Finally, the Tf-GCZSL uses a fully connected classifier developed using the synthetic features generated at the latent space of the VAE. The performance of the proposed Tf-GCZSL is evaluated in the existing task-agnostic prediction setting and the proposed task-free setting for the generalized CZSL over the five ZSL benchmark datasets. The results clearly indicate that the proposed Tf-GCZSL improves the prediction at least by 12, 1, 3, 4, and 3 over existing state-of-the-art and baseline methods for CUB, aPY, AWA1, AWA2, and SUN datasets, respectively in both settings (task-agnostic prediction and task-free learning). The source code is available at https://github.com/Chandan-IITI/Tf-GCZSL.
Item Type: | Journal Article |
---|---|
Publication: | Neural Networks |
Publisher: | Elsevier Ltd |
Additional Information: | The copyright for this article belongs to the Authors. |
Keywords: | Benchmarking; Distillation; Forecasting, Auto encoders; Boundary information; Continual learning; Continual zero-shot learning; Experience replay; Learn+; Learning frameworks; Long term memory; Training data; Variational autoencoder, Zero-shot learning, Agnostic; article; autoencoder; classifier; distillation; human; learning; long term memory; prediction; short term memory; sun |
Department/Centre: | Division of Mechanical Sciences > Aerospace Engineering(Formerly Aeronautical Engineering) |
Date Deposited: | 13 Oct 2022 04:59 |
Last Modified: | 13 Oct 2022 04:59 |
URI: | https://eprints.iisc.ac.in/id/eprint/77281 |
Actions (login required)
View Item |