mlsanityData to 7 Oct 2026

Unrealistic Feature Suppression for Generative Adversarial Networks

arXiv 2107.11047 ↗First posted 23 Jul 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Due to the unstable nature of minimax game between generator and discriminator, improving the performance of GANs is a challenging task. Recent studies have shown that selected high-quality samples in training improve the performance of GANs. However, sampling approaches which discard samples show limitations in some aspects such as the speed of training and optimality of the networks. In this paper we propose unrealistic feature suppression (UFS) module that keeps high-quality features and suppresses unrealistic features. UFS module keeps the training stability of networks and improves the quality of generated images. We demonstrate the effectiveness of UFS module on various models such as WGAN-GP, SNGAN, and BigGAN. By using UFS module, we achieved better Frechet inception distance and inception score compared to various baseline models. We also visualize how effectively our UFS module suppresses unrealistic features through class activation maps.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 33 references that are in the map. First posted on arXiv 23 Jul 2021.

Builds on

27 of 33 references.

References · 27

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  2. 2017Squeeze-and-Excitation Networkscited by 4,763
  3. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  4. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  5. 2016Improved Techniques for Training GANscited by 2,938
  6. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  7. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  8. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  9. 2017Non-local Neural Networkscited by 2,290
  10. 2017Improved Training of Wasserstein GANscited by 2,223
  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
15 more
  1. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  2. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
  3. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 925
  4. 2018Self-Attention Generative Adversarial Networkscited by 809
  5. 2017AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networkscited by 664
  6. 2016StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 575
  7. 2020Reliable Fidelity and Diversity Metrics for Generative Modelscited by 425
  8. 2018Assessing Generative Models via Precision and Recallcited by 401
  9. 2017Geometric GANcited by 232
  10. 2018Dynamic Channel Pruning: Feature Boosting and Suppressioncited by 129
  11. 2019Multi-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image Translationcited by 97
  12. 2019LOGAN: Latent Optimisation for Generative Adversarial Networkscited by 42
  13. 2020Instance Selection for GANscited by 23
  14. 2018DA-GAN: Instance-level Image Translation by Deep Attention Generative Adversarial Networks (with Supplementary Materials)cited by 21
  15. 2021Feature Boosting, Suppression, and Diversification for Fine-Grained Visual Classificationcited by 2

Built on by

Not cited yet.