Dual VAEGAN: A generative model for generalized zero-shot learning

Abstract Generalized zero-shot learning (GZSL) aims to recognize samples from all classes based on training samples of seen classes by bridging the gap between the seen and unseen classes through the semantic descriptions (attributes). Recently, generative-based methods have been used to convert the GZSL task into a supervised learning problem by generating visual features for unseen classes. In this paper, we propose a dual framework based on variational auto-encoder (VAE) and generative adversarial network (GAN), known as dual VAEGAN, to produce more clear visual features than VAE and alleviate the model collapse problem of GAN. To avoid generating unconstraint visual features, the generated visual features are forced to map back into their respective semantic space. Meanwhile, a cycle-consistency loss is used to promote diversity and preserve the semantic consistency of the generated visual features. The experimental results on the six standard datasets indicate that dual VAEGAN can produce promising results as compared with other methods reported in the literature.