mlsanityData to 7 Oct 2026

Enhancing Stability in Training Conditional Generative Adversarial Networks via Selective Data Matching

arXiv 2107.08792 ↗First posted 8 Jul 2021cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Conditional generative adversarial networks (cGANs) have demonstrated remarkable success due to their class-wise controllability and superior quality for complex generation tasks. Typical cGANs solve the joint distribution matching problem by decomposing two easier sub-problems: marginal matching and conditional matching. In this paper, we proposes a simple but effective training methodology, selective focusing learning, which enforces the discriminator and generator to learn easy samples of each class rapidly while maintaining diversity. Our key idea is to selectively apply conditional and joint matching for the data in each mini-batch.Specifically, we first select the samples with the highest scores when sorted using the conditional term of the discriminator outputs (real and generated samples). Then we optimize the model using the selected samples with only conditional matching and the other samples with joint matching. From our toy experiments, we found that it is the best to apply only conditional matching to certain samples due to the content-aware optimization of the discriminator. We conducted experiments on ImageNet (64x64 and 128x128), CIFAR-10, CIFAR-100 datasets, and Mixture of Gaussian, noisy label settings to demonstrate that the proposed method can substantially (up to 35.18% in terms of FID) improve all indicators with 10 independent trials. Code is available at https://github.com/pnu-cvsp/Enhancing-Stability-in-Training-Conditional-GAN-via-Selective-Data-Matching.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 34 of its 70 references that are in the map. First posted on arXiv 8 Jul 2021.

Builds on

34 of 70 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  5. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  6. 2016Improved Techniques for Training GANscited by 2,938
  7. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  8. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  9. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  10. 2014Conditional Generative Adversarial Netscited by 2,152
  11. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  12. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
22 more
  1. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  2. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
  3. 2017A Closer Look at Memorization in Deep Networkscited by 936
  4. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 925
  5. 2018Self-Attention Generative Adversarial Networkscited by 809
  6. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 604
  7. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 562
  8. 2020Reliable Fidelity and Diversity Metrics for Generative Modelscited by 425
  9. 2016NIPS 2016 Tutorial: Generative Adversarial Networkscited by 284
  10. 2017Automated Curriculum Learning for Neural Networkscited by 251
  11. 2019Consistency Regularization for Generative Adversarial Networkscited by 134
  12. 2015Learning with Symmetric Label Noise: The Importance of Being Unhingedcited by 120
  13. 2015Webly Supervised Learning of Convolutional Networkscited by 95
  14. 2019Bias Correction of Learned Generative Models using Likelihood-Free Importance Weightingcited by 70
  15. 2020Improved Consistency Regularization for GANscited by 67
  16. 2020Diverse Image Generation via Self-Conditioned GANscited by 54
  17. 2019Small-GAN: Speeding Up GAN Training Using Core-setscited by 40
  18. 2017ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matchingcited by 32
  19. 2020Feature Quantization Improves GAN Trainingcited by 23
  20. 2020Instance Selection for GANscited by 23
  21. 2019Twin Auxiliary Classifiers GANcited by 8
  22. 2020Top-k Training of GANs: Improving GAN Performance by Throwing Away Bad Samplescited by 4

Built on by

Not cited yet.