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.

[code] (includes links to pre-trained FSL classifiers)

BibTex Citation

@article{chochlakis2021endtoend,
  title={End-to-end {G}enerative {Z}ero-shot {L}earning via {F}ew-shot {L}earning},
  author={Chochlakis, Georgios and Georgiou, Efthymios and Potamianos, Alexandros},
  journal={arXiv preprint arXiv:2102.04379},
  year={2021}
}