GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencoder
Chen, Shiming Fu, Dingjie Khan, Salman Khan, Fahad Shahbaz
Chen, Shiming
Fu, Dingjie
Khan, Salman
Khan, Fahad Shahbaz
Supervisor
Department
Computer Vision
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Remarkable progress in zero-shot learning (ZSL) has been achieved using generative models. However, existing generative ZSL methods merely generate (imagine) the visual features from scratch guided by the strong class semantic vectors annotated by experts, resulting in suboptimal generative performance and limited scene generalization. To address these and advance ZSL, we propose an inductive variational autoencoder for generative zero-shot learning, dubbed GenZSL. Mimicking human-level concept learning, GenZSL operates by inducting new class samples from similar seen classes using weak class semantic vectors derived from target class names (i.e., CLIP text embedding). To ensure the generation of informative samples for training an effective ZSL classifier, our GenZSL incorporates two key strategies. Firstly, it employs class diversity promotion to enhance the diversity of class semantic vectors. Secondly, it utilizes target class-guided information boosting criteria to optimize the model. Extensive experiments conducted on three popular benchmark datasets showcase the superiority and potential of our GenZSL with significant efficacy and efficiency over f-VAEGAN, e.g., 24.7% performance gains and more than 60faster training speed on AWA2. Codes are available at.
Citation
S. Chen, D. Fu, S. Khan, and F. S. Khan, “GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencoder,” Oct. 06, 2025, PMLR. [Online]. Available: https://proceedings.mlr.press/v267/chen25t.html
Source
Proceedings of Machine Learning Research
Conference
42nd International Conference on Machine Learning, ICML 2025
Keywords
Subjects
Source
42nd International Conference on Machine Learning, ICML 2025
Publisher
ML Research Press