End-to-end Generative Zero-shot Learning via Few-shot Learning
This work provides an incremental improvement for researchers working on Zero-Shot Learning by integrating generative models with Few-Shot Learning.
This paper introduces Z2FSL, an end-to-end generative Zero-Shot Learning (ZSL) framework that synthesizes data and feeds it to a Few-Shot Learning (FSL) algorithm, effectively reducing ZSL to FSL. The framework achieves state-of-the-art or competitive performance on standard ZSL and Generalized ZSL benchmarks.
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.