Combating Mode Collapse in GANs via Manifold Entropy Estimation

Haozhe Liu1,2    Bing Li1     Haoqian Wu3,4     Hanbang Liang4     Yawen Huang2     Yuexiang Li2     Bernard Ghanem1     Yefeng Zheng2    

1 AI Initiative, King Abdullah University of Science and Technology (KAUST),
2 Jarvis Lab, Tencent, 3 YouTu Lab, Tencent, 4 Shenzhen University,

Abstract

     Generative Adversarial Networks (GANs) have shown compelling results in various tasks and applications in recent years. However, mode collapse remains a critical problem in GANs. In this paper, we propose a novel training pipeline to address the mode collapse issue of GANs. Different from existing methods, we propose to generalize the discriminator as feature embedding and maximize the entropy of distributions in the embedding space learned by the discriminator. Specifically, two regularization terms, i.e., Deep Local Linear Embedding (DLLE) and Deep Isometric feature Mapping (DIsoMap), are designed to encourage the discriminator to learn the structural information embedded in the data, such that the embedding space learned by the discriminator can be well-formed. Based on the well-learned embedding space supported by the discriminator, a non-parametric entropy estimator is designed to efficiently maximize the entropy of embedding vectors, playing as an approximation of maximizing the entropy of the generated distribution. By improving the discriminator and maximizing the distance of the most similar samples in the embedding space, our pipeline effectively reduces the mode collapse without sacrificing the quality of generated samples. Extensive experimental results show the effectiveness of our method which outperforms the GAN baseline, MaF-GAN on CelebA (9.13 vs. 12.43 in FID) and surpasses the recent state-of-the-art energy-based model on the ANIMEFACE dataset (2.80 vs. 2.26 in Inception score).


Paper

Code

Experimental Results

Ablation Study

Comparison with SOTA methods

Visualization

Citation


@article{liu2022combating,
  title={Combating mode collapse in gans via manifold entropy estimation},
  author={Liu, Haozhe and Li, Bing and Wu, Haoqian and Liang, Hanbang and Huang, Yawen and Li, Yuexiang 
  and Ghanem, Bernard and Zheng, Yefeng},
  journal={arXiv preprint arXiv:2208.12055},
  year={2022}
}

访问次数: stats counter