# Improving robustness against common corruptions with frequency biased models

arXiv: https://arxiv.org/abs/2103.16241 · HTML: https://mlsanity.com/paper/2103.16241/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 45 references that are in the map.
- First posted on arXiv 30 Mar 2021.

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [The Limitations of Deep Learning in Adversarial Settings](https://mlsanity.com/paper/1511.07528/) (2015)
- [AutoAugment: Learning Augmentation Policies from Data](https://mlsanity.com/paper/1805.09501/) (2018)
- [Fast is better than free: Revisiting adversarial training](https://mlsanity.com/paper/2001.03994/) (2020)
- [ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models](https://mlsanity.com/paper/1708.03999/) (2017)
- [Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods](https://mlsanity.com/paper/1705.07263/) (2017)
- [Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models](https://mlsanity.com/paper/1712.04248/) (2017)
- [Measuring Robustness to Natural Distribution Shifts in Image Classification](https://mlsanity.com/paper/2007.00644/) (2020)
- [Improving robustness against common corruptions by covariate shift adaptation](https://mlsanity.com/paper/2006.16971/) (2020)
- [Using Pre-Training Can Improve Model Robustness and Uncertainty](https://mlsanity.com/paper/1901.09960/) (2019)
- [Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming](https://mlsanity.com/paper/1907.07484/) (2019)
- [Feature Denoising for Improving Adversarial Robustness](https://mlsanity.com/paper/1812.03411/) (2018)
- [A Fourier Perspective on Model Robustness in Computer Vision](https://mlsanity.com/paper/1906.08988/) (2019)
- [Generalisation in humans and deep neural networks](https://mlsanity.com/paper/1808.08750/) (2018)
- [Efficient Decision-based Black-box Adversarial Attacks on Face Recognition](https://mlsanity.com/paper/1904.04433/) (2019)
- [Adversarial Examples Are a Natural Consequence of Test Error in Noise](https://mlsanity.com/paper/1901.10513/) (2019)
- [Benchmarking the Robustness of Semantic Segmentation Models](https://mlsanity.com/paper/1908.05005/) (2019)

## Built on by (most cited first, 30 of 34)

- [DriveSuprim: Towards Precise Trajectory Selection for End-to-End Planning](https://mlsanity.com/paper/2506.06659/) (2025)
- [Assaying Out-Of-Distribution Generalization in Transfer Learning](https://mlsanity.com/paper/2207.09239/) (2022)
- [PRIME: A few primitives can boost robustness to common corruptions](https://mlsanity.com/paper/2112.13547/) (2021)
- [WEDGE: A multi-weather autonomous driving dataset built from generative vision-language models](https://mlsanity.com/paper/2305.07528/) (2023)
- [A Survey on the Robustness of Computer Vision Models against Common Corruptions](https://mlsanity.com/paper/2305.06024/) (2023)
- [Can Biases in ImageNet Models Explain Generalization?](https://mlsanity.com/paper/2404.01509/) (2024)
- [Fourier-basis Functions to Bridge Augmentation Gap: Rethinking Frequency Augmentation in Image Classification](https://mlsanity.com/paper/2403.01944/) (2024)
- [Improving Robustness by Enhancing Weak Subnets](https://mlsanity.com/paper/2201.12765/) (2022)
- [Classification robustness to common optical aberrations](https://mlsanity.com/paper/2308.15499/) (2023)
- [Continual BatchNorm Adaptation (CBNA) for Semantic Segmentation](https://mlsanity.com/paper/2203.01074/) (2022)
- [HybridAugment++: Unified Frequency Spectra Perturbations for Model Robustness](https://mlsanity.com/paper/2307.11823/) (2023)
- [Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptions](https://mlsanity.com/paper/2403.20254/) (2024)
- [How Does Frequency Bias Affect the Robustness of Neural Image Classifiers against Common Corruption and Adversarial Perturbations?](https://mlsanity.com/paper/2205.04533/) (2022)
- [Dynamic Sparse Training versus Dense Training: The Unexpected Winner in Image Corruption Robustness](https://mlsanity.com/paper/2410.03030/) (2024)
- [An Extended Study of Human-like Behavior under Adversarial Training](https://mlsanity.com/paper/2303.12669/) (2023)
- [Improving Model Generalization by On-manifold Adversarial Augmentation in the Frequency Domain](https://mlsanity.com/paper/2302.14302/) (2023)
- [Robust Asymmetric Heterogeneous Federated Learning with Corrupted Clients](https://mlsanity.com/paper/2503.09206/) (2025)
- [Assessment Framework for Deepfake Detection in Real-world Situations](https://mlsanity.com/paper/2304.06125/) (2023)
- [Addressing Mistake Severity in Neural Networks with Semantic Knowledge](https://mlsanity.com/paper/2211.11880/) (2022)
- [Estimating the Robustness of Classification Models by the Structure of the Learned Feature-Space](https://mlsanity.com/paper/2106.12303/) (2021)
- [Fourier Analysis on Robustness of Graph Convolutional Neural Networks for Skeleton-based Action Recognition](https://mlsanity.com/paper/2305.17939/) (2023)
- [A Modular System for Enhanced Robustness of Multimedia Understanding Networks via Deep Parametric Estimation](https://mlsanity.com/paper/2402.18402/) (2024)
- [DGSSA: Domain generalization with structural and stylistic augmentation for retinal vessel segmentation](https://mlsanity.com/paper/2501.03466/) (2025)
- [Examining the Impact of Optical Aberrations to Image Classification and Object Detection Models](https://mlsanity.com/paper/2504.18510/) (2025)
- [Fourier Sensitivity and Regularization of Computer Vision Models](https://mlsanity.com/paper/2301.13514/) (2023)
- [FFT-based Selection and Optimization of Statistics for Robust Recognition of Severely Corrupted Images](https://mlsanity.com/paper/2403.14335/) (2024)
- [Adaptive Sensitivity Analysis for Robust Augmentation against Natural Corruptions in Image Segmentation](https://mlsanity.com/paper/2406.01425/) (2024)
- [A Validation Strategy for Deep Learning Models: Evaluating and Enhancing Robustness](https://mlsanity.com/paper/2509.19197/) (2025)
- [t-RAIN: Robust generalization under weather-aliasing label shift attacks](https://mlsanity.com/paper/2305.08302/) (2023)
- [Exploiting Frequency Spectrum of Adversarial Images for General Robustness](https://mlsanity.com/paper/2305.08439/) (2023)

## Abstract (arXiv)

CNNs perform remarkably well when the training and test distributions are i.i.d, but unseen image corruptions can cause a surprisingly large drop in performance. In various real scenarios, unexpected distortions, such as random noise, compression artefacts, or weather distortions are common phenomena. Improving performance on corrupted images must not result in degraded i.i.d performance - a challenge faced by many state-of-the-art robust approaches. Image corruption types have different characteristics in the frequency spectrum and would benefit from a targeted type of data augmentation, which, however, is often unknown during training. In this paper, we introduce a mixture of two expert models specializing in high and low-frequency robustness, respectively. Moreover, we propose a new regularization scheme that minimizes the total variation (TV) of convolution feature-maps to increase high-frequency robustness. The approach improves on corrupted images without degrading in-distribution performance. We demonstrate this on ImageNet-C and also for real-world corruptions on an automotive dataset, both for object classification and object detection.