Distribution Fitting for Combating Mode Collapse in Generative Adversarial Networks
Not on the map. Why?
Abstract (arXiv)
Mode collapse is a significant unsolved issue of generative adversarial networks. In this work, we examine the causes of mode collapse from a novel perspective. Due to the nonuniform sampling in the training process, some sub-distributions may be missed when sampling data. As a result, even when the generated distribution differs from the real one, the GAN objective can still achieve the minimum. To address the issue, we propose a global distribution fitting (GDF) method with a penalty term to confine the generated data distribution. When the generated distribution differs from the real one, GDF will make the objective harder to reach the minimal value, while the original global minimum is not changed. To deal with the circumstance when the overall real data is unreachable, we also propose a local distribution fitting (LDF) method. Experiments on several benchmarks demonstrate the effectiveness and competitive performance of GDF and LDF.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 35 of its 51 references that are in the map. First posted on arXiv 3 Dec 2022.
Builds on
35 of 51 references.
References · 35
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
- 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
- 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
- 2016Improved Techniques for Training GANscited by 2,970
- 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
- 2017Improved Training of Wasserstein GANscited by 2,235
- 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
- 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
- 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,098
- 2018Which Training Methods for GANs do actually Converge?cited by 679
- 2019MaskGAN: Towards Diverse and Interactive Facial Image Manipulationcited by 628
23 more
- 2017Geometric GANcited by 233
- 2016Adversarially Learned Inferencecited by 216
- 2016Unrolled Generative Adversarial Networkscited by 208
- 2017VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learningcited by 200
- 2019Mode Seeking Generative Adversarial Networks for Diverse Image Synthesiscited by 138
- 2016Mode Regularized Generative Adversarial Networkscited by 123
- 2017BEGAN: Boundary Equilibrium Generative Adversarial Networkscited by 121
- 2017PacGAN: The power of two samples in generative adversarial networkscited by 104
- 2019Bias Correction of Learned Generative Models using Likelihood-Free Importance Weightingcited by 70
- 2018On GANs and GMMscited by 62
- 2017Multi-Agent Diverse Generative Adversarial Networkscited by 59
- 2017Dual Discriminator Generative Adversarial Netscited by 55
- 2020Diverse Image Generation via Self-Conditioned GANscited by 55
- 2020Inclusive GAN: Improving Data and Minority Coverage in Generative Modelscited by 44
- 2021DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Networkcited by 37
- 2017AdaGAN: Boosting Generative Modelscited by 34
- 2019Spectral Regularization for Combating Mode Collapse in GANscited by 33
- 2018Dist-GAN: An Improved GAN using Distance Constraintscited by 26
- 2018MGGAN: Solving Mode Collapse using Manifold Guided Trainingcited by 22
- 2020Simple and Effective Prevention of Mode Collapse in Deep One-Class Classificationcited by 17
- 2018Mixture Density Generative Adversarial Networkscited by 9
- 2020Dual Adversarial Auto-Encoders for Clusteringcited by 7
- 2020Stabilizing Training of Generative Adversarial Nets via Langevin Stein Variational Gradient Descentcited by 5
Built on by
Not cited yet.