Rethinking Multidimensional Discriminator Output for Generative Adversarial Networks
Not on the map. Why?
Abstract (arXiv)
The study of multidimensional discriminator (critic) output for Generative Adversarial Networks has been underexplored in the literature. In this paper, we generalize the Wasserstein GAN framework to take advantage of multidimensional critic output and explore its properties. We also introduce a square-root velocity transformation (SRVT) block which favors training in the multidimensional setting. Proofs of properties are based on our proposed maximal p-centrality discrepancy, which is bounded above by p-Wasserstein distance and fits the Wasserstein GAN framework with multidimensional critic output n. Especially when n = 1 and p = 1, the proposed discrepancy equals 1-Wasserstein distance. Theoretical analysis and empirical evidence show that high-dimensional critic output has its advantage on distinguishing real and fake distributions, and benefits faster convergence and diversity of results.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 35 of its 52 references that are in the map. First posted on arXiv 8 Sep 2021.
Builds on
35 of 52 references.
References · 35
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2016Densely Connected Convolutional Networkscited by 6,691
- 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
- 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
- 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
- 2017Improved Training of Wasserstein GANscited by 2,223
- 2016Identity Mappings in Deep Residual Networkscited by 1,960
- 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
- 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
- 2018Demystifying MMD GANscited by 1,268
- 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
- 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
23 more
- 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
- 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 460
- 2018Assessing Generative Models via Precision and Recallcited by 401
- 2015Generative Moment Matching Networkscited by 252
- 2017MMD GAN: Towards Deeper Understanding of Moment Matching Networkcited by 251
- 2019Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptationcited by 235
- 2019Generalized Sliced Wasserstein Distancescited by 205
- 2015Training generative neural networks via Maximum Mean Discrepancy optimizationcited by 149
- 2019Consistency Regularization for Generative Adversarial Networkscited by 134
- 2019Max-Sliced Wasserstein Distance and its use for GANscited by 118
- 2018Generative Modeling using the Sliced Wasserstein Distancecited by 108
- 2017Fisher-Rao Metric, Geometry, and Complexity of Neural Networkscited by 99
- 2020House-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout Generationcited by 86
- 2015Sliced Wasserstein Kernels for Probability Distributionscited by 64
- 2019Sliced Wasserstein Generative Modelscited by 61
- 2018Improving the Improved Training of Wasserstein GANs: A Consistency Term and Its Dual Effectcited by 49
- 2020Refining Deep Generative Models via Discriminator Gradient Flowcited by 45
- 2021Wasserstein GANs Work Because They Fail (to Approximate the Wasserstein Distance)cited by 33
- 2019A Characteristic Function Approach to Deep Implicit Generative Modelingcited by 25
- 2020GAN Ensemble for Anomaly Detectioncited by 22
- 2017McGan: Mean and Covariance Feature Matching GANcited by 21
- 2015Understanding symmetries in deep networkscited by 17
- 2019Constrained Generative Adversarial Networks for Interactive Image Generationcited by 10
Built on by
Citing papers per year: 2021: 1.
1 paper.