# Spatial Frequency Bias in Convolutional Generative Adversarial Networks

arXiv: https://arxiv.org/abs/2010.01473 · HTML: https://mlsanity.com/paper/2010.01473/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Oct 2020.

## Built on by (most cited first, 30 of 35)

- [FreeU: Free Lunch in Diffusion U-Net](https://mlsanity.com/paper/2309.11497/) (2023)
- [Diffusion Probabilistic Model Made Slim](https://mlsanity.com/paper/2211.17106/) (2022)
- [Towards the Detection of Diffusion Model Deepfakes](https://mlsanity.com/paper/2210.14571/) (2022)
- [Preserving Fairness Generalization in Deepfake Detection](https://mlsanity.com/paper/2402.17229/) (2024)
- [A Closer Look at Fourier Spectrum Discrepancies for CNN-generated Images Detection](https://mlsanity.com/paper/2103.17195/) (2021)
- [On the Frequency Bias of Generative Models](https://mlsanity.com/paper/2111.02447/) (2021)
- [ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake Images](https://mlsanity.com/paper/2112.03553/) (2021)
- [Quality-Agnostic Deepfake Detection with Intra-model Collaborative Learning](https://mlsanity.com/paper/2309.05911/) (2023)
- [Parents and Children: Distinguishing Multimodal DeepFakes from Natural Images](https://mlsanity.com/paper/2304.00500/) (2023)
- [On the Activation Function Dependence of the Spectral Bias of Neural Networks](https://mlsanity.com/paper/2208.04924/) (2022)
- [Discovering Transferable Forensic Features for CNN-generated Images Detection](https://mlsanity.com/paper/2208.11342/) (2022)
- [A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shot](https://mlsanity.com/paper/2307.14397/) (2023)
- [Beta Sampling is All You Need: Efficient Image Generation Strategy for Diffusion Models using Stepwise Spectral Analysis](https://mlsanity.com/paper/2407.12173/) (2024)
- [On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlook](https://mlsanity.com/paper/2307.16680/) (2023)
- [Exploring The Effect of High-frequency Components in GANs Training](https://mlsanity.com/paper/2103.11093/) (2021)
- [Exploring the Asynchronous of the Frequency Spectra of GAN-generated Facial Images](https://mlsanity.com/paper/2112.08050/) (2021)
- [On the Effectiveness of Spectral Discriminators for Perceptual Quality Improvement](https://mlsanity.com/paper/2307.12027/) (2023)
- [Improving Feature Stability during Upsampling -- Spectral Artifacts and the Importance of Spatial Context](https://mlsanity.com/paper/2311.17524/) (2023)
- [Simpler is better: spectral regularization and up-sampling techniques for variational autoencoders](https://mlsanity.com/paper/2201.07544/) (2022)
- [Improved Training Technique for Shortcut Models](https://mlsanity.com/paper/2510.21250/) (2025)
- [Emergent Asymmetry of Precision and Recall for Measuring Fidelity and Diversity of Generative Models in High Dimensions](https://mlsanity.com/paper/2306.09618/) (2023)
- [Model Synthesis for Zero-Shot Model Attribution](https://mlsanity.com/paper/2307.15977/) (2023)
- [WINE: Wavelet-Guided GAN Inversion and Editing for High-Fidelity Refinement](https://mlsanity.com/paper/2210.09655/) (2022)
- [Rethinking Individual Fairness in Deepfake Detection](https://mlsanity.com/paper/2507.14326/) (2025)
- [Low-frequency Image Deep Steganography: Manipulate the Frequency Distribution to Hide Secrets with Tenacious Robustness](https://mlsanity.com/paper/2303.13713/) (2023)
- [Data augmentation and explainability for bias discovery and mitigation in deep learning](https://mlsanity.com/paper/2308.09464/) (2023)
- [A survey on bias in machine learning research](https://mlsanity.com/paper/2308.11254/) (2023)
- [Unpaired Optical Coherence Tomography Angiography Image Super-Resolution via Frequency-Aware Inverse-Consistency GAN](https://mlsanity.com/paper/2309.17269/) (2023)
- [On the potential of sequential and non-sequential regression models for Sentinel-1-based biomass prediction in Tanzanian miombo forests](https://mlsanity.com/paper/2106.15020/) (2021)
- [Will the Inclusion of Generated Data Amplify Bias Across Generations in Future Image Classification Models?](https://mlsanity.com/paper/2410.10160/) (2024)

## Abstract (arXiv)

As the success of Generative Adversarial Networks (GANs) on natural images quickly propels them into various real-life applications across different domains, it becomes more and more important to clearly understand their limitations. Specifically, understanding GANs' capability across the full spectrum of spatial frequencies, i.e. beyond the low-frequency dominant spectrum of natural images, is critical for assessing the reliability of GAN generated data in any detail-sensitive application (e.g. denoising, filling and super-resolution in medical and satellite images). In this paper, we show that the ability of convolutional GANs to learn a distribution is significantly affected by the spatial frequency of the underlying carrier signal, that is, GANs have a bias against learning high spatial frequencies. Crucially, we show that this bias is not merely a result of the scarcity of high frequencies in natural images, rather, it is a systemic bias hindering the learning of high frequencies regardless of their prominence in a dataset. Furthermore, we explain why large-scale GANs' ability to generate fine details on natural images does not exclude them from the adverse effects of this bias. Finally, we propose a method for manipulating this bias with minimal computational overhead. This method can be used to explicitly direct computational resources towards any specific spatial frequency of interest in a dataset, extending the flexibility of GANs.