# Investigating and Explaining the Frequency Bias in Image Classification

arXiv: https://arxiv.org/abs/2205.03154 · HTML: https://mlsanity.com/paper/2205.03154/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 16 references that are in the map.
- First posted on arXiv 6 May 2022.

## Builds on (most cited first, 10 of 10)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks](https://mlsanity.com/paper/1905.13545/) (2019)
- [Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributions](https://mlsanity.com/paper/2003.01826/) (2020)
- [Fourier Spectrum Discrepancies in Deep Network Generated Images](https://mlsanity.com/paper/1911.06465/) (2019)
- [Measuring the tendency of CNNs to Learn Surface Statistical Regularities](https://mlsanity.com/paper/1711.11561/) (2017)
- [On the Frequency Bias of Generative Models](https://mlsanity.com/paper/2111.02447/) (2021)

## Built on by (most cited first, 8 of 8)

- [Frequency-Aligned Knowledge Distillation for Lightweight Spatiotemporal Forecasting](https://mlsanity.com/paper/2507.02939/) (2025)
- [Noise Matters: Optimizing Matching Noise for Diffusion Classifiers](https://mlsanity.com/paper/2508.11330/) (2025)
- [Exploring connections of spectral analysis and transfer learning in medical imaging](https://mlsanity.com/paper/2407.11379/) (2024)
- [A Gift from the Integration of Discriminative and Diffusion-based Generative Learning: Boundary Refinement Remote Sensing Semantic Segmentation](https://mlsanity.com/paper/2507.01573/) (2025)
- [Exploiting Frequency Spectrum of Adversarial Images for General Robustness](https://mlsanity.com/paper/2305.08439/) (2023)
- [Interpreting Adversarial Attacks and Defences using Architectures with Enhanced Interpretability](https://mlsanity.com/paper/2502.15017/) (2025)
- [DuFal: Dual-Frequency-Aware Learning for High-Fidelity Extremely Sparse-view CBCT Reconstruction](https://mlsanity.com/paper/2601.15416/) (2026)
- [Low-Frequency Shortcuts in Texture-Driven Visual Learning](https://mlsanity.com/paper/2606.03493/) (2026)

## Abstract (arXiv)

CNNs exhibit many behaviors different from humans, one of which is the capability of employing high-frequency components. This paper discusses the frequency bias phenomenon in image classification tasks: the high-frequency components are actually much less exploited than the low- and mid-frequency components. We first investigate the frequency bias phenomenon by presenting two observations on feature discrimination and learning priority. Furthermore, we hypothesize that (i) the spectral density, (ii) class consistency directly affect the frequency bias. Specifically, our investigations verify that the spectral density of datasets mainly affects the learning priority, while the class consistency mainly affects the feature discrimination.