F-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning

Abstract

When labeled training data is scarce, a promising data augmentation approach is to generate visual features of un- known classes using their attributes. To learn the class conditional distribution of CNN features, these models rely on pairs of image features and class attributes. Hence, they can not make use of the abundance of unlabeled data samples. In this paper, we tackle any-shot learning problems i.e. zero-shot and few-shot, in a unified feature generating framework that operates in both inductive and transductive learning settings. We develop a conditional generative model that combines the strength of VAE and GANs and in addition, via an unconditional discriminator, learns the marginal feature distribution of unlabeled images. We empirically show that our model learns highly discriminative CNN features for CUB and FLO datasets, and establish a new state-of-the-art in any-shot learning, i.e. inductive and transductive generalized zero- and few-shot learning settings.