Zero-shot learning (ZSL) aims to recognize the novel classes which cannot be collected for training a prediction model. Accordingly, generative models [e.g., generative adversarial network (GAN)] are typically used to synthesize the visual samples conditioned by the class semantic vectors and achieve remarkable progress for ZSL. However, existing GAN-based generative ZSL methods are based on hand-crafted models, which cannot adapt to various datasets/scenarios and fails to model instability. To alleviate these challenges, we propose evolutionary GAN search (termed EGANS) to automatically design the generative network with good adaptation and stability, enabling reliable visual feature sample synthesis for advancing ZSL. Specifically, we adopt cooperative dual evolution to conduct a neural architecture search (NAS) for both generator and discriminator under a unified evolutionary adversarial framework. EGANS is learned by two stages: 1) evolution generator architecture search and 2) evolution discriminator architecture search. During the evolution generator architecture search, we adopt a many-to-one adversarial training strategy to evolutionarily search for the optimal generator. Then the optimal generator is further applied to search for the optimal discriminator in the evolution discriminator architecture search with a similar evolution search algorithm. Once the optimal generator and discriminator are searched, we entail them into various generative ZSL baselines for ZSL classification. Extensive experiments show that EGANS consistently improve existing generative ZSL methods on the standard CUB, SUN, AWA2 and FLO datasets. The significant performance gains indicate that the evolutionary NAS explores a virgin field in ZSL.
