Continual Learning Improves Zero-Shot Action Recognition

Gowda, Shreyank N.; Moltisanti, Davide; Sevilla-Lara, Laura

Abstract

Zero-shot action recognition requires a strong ability to generalize from pre-training and seen classes to novel unseen classes. Similarly, continual learning aims to develop models that can generalize effectively and learn new tasks without forgetting the ones previously learned. The generalization goals of zero-shot and continual learning are closely aligned, however techniques from continual learning have not been applied to zero-shot action recognition. In this paper, we propose a novel method based on continual learning to address zero-shot action recognition. This model, which we call Generative Iterative Learning (GIL) uses a memory of synthesized features of past classes, and combines these synthetic features with real ones from novel classes. The memory is used to train a classification model, ensuring a balanced exposure to both old and new classes. Experiments demonstrate that GIL improves generalization in unseen classes, achieving a new state-of-the-art in zero-shot recognition across multiple benchmarks. Importantly, GIL also boosts performance in the more challenging generalized zero-shot setting, where models need to retain knowledge about classes seen before fine-tuning.

Citation

Gowda, S. N., Moltisanti, D., & Sevilla-Lara, L. (2024, December). Continual Learning Improves Zero-Shot Action Recognition. Presented at Computer Vision – ACCV 2024 17th Asian Conference on Computer Vision, Hanoi, Vietnam

• Presentation Conference Type: Edited Proceedings
• Conference Name: Computer Vision – ACCV 2024 17th Asian Conference on Computer Vision
• Start Date: Dec 8, 2024
• End Date: Dec 12, 2024
• Acceptance Date: Dec 7, 2024
• Online Publication Date: Dec 7, 2024
• Publication Date: Dec 8, 2024
• Deposit Date: Feb 28, 2025
• Publicly Available Date: Mar 14, 2025
• Peer Reviewed: Peer Reviewed
• Pages: 403-421
• Series Title: Lecture Notes in Computer Science
• Series Number: 15474
• Series ISSN: 1611-3349
• Book Title: Computer Vision – ACCV 2024 17th Asian Conference on Computer Vision, Hanoi, Vietnam, December 8–12, 2024, Proceedings, Part III
• ISBN: 9789819609079
• DOI: https://doi.org/10.1007/978-981-96-0908-6_23
• Public URL: https://nottingham-repository.worktribe.com/output/45861183
• Publisher URL: https://link.springer.com/chapter/10.1007/978-981-96-0908-6_23