MetaZSCIL: A Meta-Learning Approach for Generalized Zero-Shot Class Incremental Learning
Open Access
- 26 June 2023
- journal article
- research article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (9) , 10408-10416
Abstract
Generalized zero-shot learning (GZSL) aims to recognize samples whose categories may not have been seen at training. Standard GZSL cannot handle dynamic addition of new seen and unseen classes. In order to address this limitation, some recent attempts have been made to develop continual GZSL methods. However, these methods require end-users to continuously collect and annotate numerous seen class samples, which is unrealistic and hampers the applicability in the real-world. Accordingly, in this paper, we propose a more practical and challenging setting named Generalized Zero-Shot Class Incremental Learning (CI-GZSL). Our setting aims to incrementally learn unseen classes without any training samples, while recognizing all classes previously encountered. We further propose a bi-level meta-learning based method called MetaZSCIL to directly optimize the network to learn how to incrementally learn. Specifically, we sample sequential tasks from seen classes during the offline training to simulate the incremental learning process. For each task, the model is learned using a meta-objective such that it is capable to perform fast adaptation without forgetting. Note that our optimization can be flexibly equipped with most existing generative methods to tackle CI-GZSL. This work introduces a feature generative framework that leverages visual feature distribution alignment to produce replayed samples of previously seen classes to reduce catastrophic forgetting. Extensive experiments conducted on five widely used benchmarks demonstrate the superiority of our proposed method.Keywords
This publication has 7 references indexed in Scilit:
- Tf-GCZSL: Task-free generalized continual zero-shot learningNeural Networks, 2022
- Discriminative Metric Learning for Partial Label LearningIEEE Transactions on Neural Networks and Learning Systems, 2021
- Incremental Zero-Shot LearningIEEE Transactions on Cybernetics, 2021
- Top-k Partial Label MachineIEEE Transactions on Neural Networks and Learning Systems, 2021
- Zero-Shot Learning—A Comprehensive Evaluation of the Good, the Bad and the UglyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- Metric Learning for Multi-Output TasksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- Attribute-Based Classification for Zero-Shot Visual Object CategorizationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013