Publications
End-to-end generative zero-shot learning via few-shot learning
Abstract
Contemporary state-of-the-art approaches to Zero-Shot Learning (ZSL) train generative nets to synthesize examples conditioned on the provided metadata. Thereafter, classifiers are trained on these synthetic data in a supervised manner. In this work, we introduce Z2FSL, an end-to-end generative ZSL framework that uses such an approach as a backbone and feeds its synthesized output to a Few-Shot Learning (FSL) algorithm. The two modules are trained jointly. Z2FSL solves the ZSL problem with a FSL algorithm, reducing, in effect, ZSL to FSL. A wide class of algorithms can be integrated within our framework. Our experimental results show consistent improvement over several baselines. The proposed method, evaluated across standard benchmarks, shows state-of-the-art or competitive performance in ZSL and Generalized ZSL tasks.
Metadata
- publication
- arXiv preprint arXiv:2102.04379, 2021
- year
- 2021
- publication date
- 2021/2/8
- authors
- Georgios Chochlakis, Efthymios Georgiou, Alexandros Potamianos
- link
- https://arxiv.org/abs/2102.04379
- resource_link
- https://arxiv.org/pdf/2102.04379
- journal
- arXiv preprint arXiv:2102.04379