EGANS: Evolutionary Generative Adversarial Network Search for Zero-Shot Learning
- 21 August 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Evolutionary Computation
- Vol. 28 (3) , 582-596
Abstract
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 generative adversarial network 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 for both generator and discriminator under a unified evolutionary adversarial framework. EGANS is learned by two stages: evolution generator architecture search and 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 neural architecture search explores a virgin field in ZSL.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62172177, 61976120)
- National Key Research and Development Program of China (2022YFC3301004, 2022YFC3301003, 2022YFC3301704, 2022YFF0712300)
- Natural Science Foundation of Jiangsu Province (BK20191445)
- Natural Science Key Foundation of Jiangsu Education Department (21KJA510004)
This publication has 63 references indexed in Scilit:
- EAGAN: Efficient Two-Stage Evolutionary Architecture Search for GANs2022
- Semantically Tied Paired Cycle Consistency for Any-Shot Sketch-Based Image RetrievalInternational Journal of Computer Vision, 2020
- MnasNet: Platform-Aware Neural Architecture Search for Mobile2019
- Coevolution of Generative Adversarial Networks2019
- Multi-modal Cycle-Consistent Generalized Zero-Shot Learning2018
- Zero-Shot Object Detection2018
- Zero-Shot Sketch-Image Hashing2018
- Feature Generating Networks for Zero-Shot Learning2018
- Transductive Unbiased Embedding for Zero-Shot Learning2018
- Zero-Shot Visual Recognition via Bidirectional Latent EmbeddingInternational Journal of Computer Vision, 2017