mlsanityData to 7 Oct 2026

Explicit Use of Fourier Spectrum in Generative Adversarial Networks

arXiv 2208.01265 ↗First posted 2 Aug 2022cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Generative Adversarial Networks have got the researchers' attention due to their state-of-the-art performance in generating new images with only a dataset of the target distribution. It has been shown that there is a dissimilarity between the spectrum of authentic images and fake ones. Since the Fourier transform is a bijective mapping, saying that the model has a significant problem in learning the original distribution is a fair conclusion. In this work, we investigate the possible reasons for the mentioned drawback in the architecture and mathematical theory of the current GANs. Then we propose a new model to reduce the discrepancies between the spectrum of the actual and fake images. To that end, we design a brand new architecture for the frequency domain using the blueprint of geometric deep learning. Then, we experimentally show promising improvements in the quality of the generated images by considering the Fourier domain representation of the original data as a principal feature in the training process.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 48 of its 75 references that are in the map. First posted on arXiv 2 Aug 2022.

Builds on

48 of 75 references.

References · 48

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2017Mask R-CNNcited by 7,259
  5. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  6. 2022Generative Adversarial Networkscited by 5,603
  7. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  8. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  9. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  10. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  11. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  12. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
36 more
  1. 2017Improved Training of Wasserstein GANscited by 2,223
  2. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  3. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  4. 2018On the Spectral Bias of Neural Networkscited by 1,321
  5. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  6. 2014Convolutional Neural Networks for Sentence Classificationcited by 1,124
  7. 2016Least Squares Generative Adversarial Networkscited by 1,000
  8. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 842
  9. 2016StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 575
  10. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  11. 2018Image Inpainting for Irregular Holes Using Partial Convolutionscited by 505
  12. 2020Leveraging Frequency Analysis for Deep Fake Image Recognitioncited by 501
  13. 2019Detecting and Simulating Artifacts in GAN Fake Imagescited by 293
  14. 2020Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributionscited by 278
  15. 2019Large Scale Adversarial Representation Learningcited by 238
  16. 2013OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networkscited by 224
  17. 2018Pros and Cons of GAN Evaluation Measurescited by 224
  18. 2016Coupled Generative Adversarial Networkscited by 216
  19. 2017Image De-raining Using a Conditional Generative Adversarial Networkcited by 197
  20. 2020Learning in the Frequency Domaincited by 196
  21. 2014A Convolutional Neural Network for Modelling Sentencescited by 163
  22. 2014Simultaneous Detection and Segmentationcited by 158
  23. 2019Implicit regularization for deep neural networks driven by an Ornstein-Uhlenbeck like processcited by 123
  24. 20163D Shape Induction from 2D Views of Multiple Objectscited by 121
  25. 2016Invertible Conditional GANs for image editingcited by 118
  26. 2020Implicit Regularization in Deep Learning May Not Be Explainable by Normscited by 118
  27. 2016Neural Photo Editing with Introspective Adversarial Networkscited by 109
  28. 2016Learning What and Where to Drawcited by 105
  29. 2021Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forwardcited by 82
  30. 2020SSD-GAN: Measuring the Realness in the Spatial and Spectral Domainscited by 38
  31. 2017TAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Networkcited by 21
  32. 2021SWAGAN: A Style-based Wavelet-driven Generative Modelcited by 17
  33. 2020Mimicry: Towards the Reproducibility of GAN Researchcited by 14
  34. 2019Band-limited Training and Inference for Convolutional Neural Networkscited by 13
  35. 2018Highly Scalable Image Reconstruction using Deep Neural Networks with Bandpass Filteringcited by 4
  36. 2019A New Perspective on Machine Learning: How to do Perfect Supervised Learningcited by 1

Built on by

Not cited yet.