# Impact of Aliasing on Generalization in Deep Convolutional Networks

arXiv: https://arxiv.org/abs/2108.03489 · HTML: https://mlsanity.com/paper/2108.03489/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 32 references that are in the map.
- First posted on arXiv 7 Aug 2021.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [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)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [AutoAugment: Learning Augmentation Policies from Data](https://mlsanity.com/paper/1805.09501/) (2018)
- [Making Convolutional Networks Shift-Invariant Again](https://mlsanity.com/paper/1904.11486/) (2019)
- [Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples](https://mlsanity.com/paper/1903.03096/) (2019)
- [A Fourier Perspective on Model Robustness in Computer Vision](https://mlsanity.com/paper/1906.08988/) (2019)
- [Why do deep convolutional networks generalize so poorly to small image transformations?](https://mlsanity.com/paper/1805.12177/) (2018)
- [Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes](https://mlsanity.com/paper/1906.07697/) (2019)
- [Smooth Adversarial Training](https://mlsanity.com/paper/2006.14536/) (2020)
- [A Universal Representation Transformer Layer for Few-Shot Image Classification](https://mlsanity.com/paper/2006.11702/) (2020)
- [Delving Deeper into Anti-aliasing in ConvNets](https://mlsanity.com/paper/2008.09604/) (2020)
- [A Corrective View of Neural Networks: Representation, Memorization and Learning](https://mlsanity.com/paper/2002.00274/) (2020)
- [Selecting Relevant Features from a Multi-domain Representation for Few-shot Classification](https://mlsanity.com/paper/2003.09338/) (2020)

## Built on by (most cited first, 25 of 25)

- [Analyzing and Improving the Training Dynamics of Diffusion Models](https://mlsanity.com/paper/2312.02696/) (2023)
- [FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes](https://mlsanity.com/paper/2110.08059/) (2021)
- [Towards Stability of Autoregressive Neural Operators](https://mlsanity.com/paper/2306.10619/) (2023)
- [The Lie Derivative for Measuring Learned Equivariance](https://mlsanity.com/paper/2210.02984/) (2022)
- [Shift-tolerant Perceptual Similarity Metric](https://mlsanity.com/paper/2207.13686/) (2022)
- [ConDA: Unsupervised Domain Adaptation for LiDAR Segmentation via Regularized Domain Concatenation](https://mlsanity.com/paper/2111.15242/) (2021)
- [Frequency-Adaptive Dilated Convolution for Semantic Segmentation](https://mlsanity.com/paper/2403.05369/) (2024)
- [Temporally Consistent Online Depth Estimation Using Point-Based Fusion](https://mlsanity.com/paper/2304.07435/) (2023)
- [Anti-aliasing Deep Image Classifiers using Novel Depth Adaptive Blurring and Activation Function](https://mlsanity.com/paper/2110.00899/) (2021)
- [Exploration into Translation-Equivariant Image Quantization](https://mlsanity.com/paper/2112.00384/) (2021)
- [How Does Frequency Bias Affect the Robustness of Neural Image Classifiers against Common Corruption and Adversarial Perturbations?](https://mlsanity.com/paper/2205.04533/) (2022)
- [HFI: A unified framework for training-free detection and implicit watermarking of latent diffusion model generated images](https://mlsanity.com/paper/2412.20704/) (2024)
- [Dynamic Test-Time Augmentation via Differentiable Functions](https://mlsanity.com/paper/2212.04681/) (2022)
- [DNArch: Learning Convolutional Neural Architectures by Backpropagation](https://mlsanity.com/paper/2302.05400/) (2023)
- [MULLER: Multilayer Laplacian Resizer for Vision](https://mlsanity.com/paper/2304.02859/) (2023)
- [Group Downsampling with Equivariant Anti-aliasing](https://mlsanity.com/paper/2504.17258/) (2025)
- [The Importance of Anti-Aliasing in Tiny Object Detection](https://mlsanity.com/paper/2310.14221/) (2023)
- [Aliasing is a Driver of Adversarial Attacks](https://mlsanity.com/paper/2212.11760/) (2022)
- [A Comprehensive Assessment Benchmark for Rigorously Evaluating Deep Learning Image Classifiers](https://mlsanity.com/paper/2308.04137/) (2023)
- [Gradient-Free Adversarial Purification with Diffusion Models](https://mlsanity.com/paper/2501.13336/) (2025)
- [WD-DETR: Wavelet Denoising-Enhanced Real-Time Object Detection Transformer for Robot Perception with Event Cameras](https://mlsanity.com/paper/2506.09098/) (2025)
- [Studying inductive biases in image classification task](https://mlsanity.com/paper/2210.17141/) (2022)
- [Anti-aliasing Predictive Coding Network for Future Video Frame Prediction](https://mlsanity.com/paper/2301.05421/) (2023)
- [Fix your downsampling ASAP! Be natively more robust via Aliasing and Spectral Artifact free Pooling](https://mlsanity.com/paper/2307.09804/) (2023)
- [A New Multimodal Medical Image Fusion based on Laplacian Autoencoder with Channel Attention](https://mlsanity.com/paper/2310.11896/) (2023)

## Abstract (arXiv)

We investigate the impact of aliasing on generalization in Deep Convolutional Networks and show that data augmentation schemes alone are unable to prevent it due to structural limitations in widely used architectures. Drawing insights from frequency analysis theory, we take a closer look at ResNet and EfficientNet architectures and review the trade-off between aliasing and information loss in each of their major components. We show how to mitigate aliasing by inserting non-trainable low-pass filters at key locations, particularly where networks lack the capacity to learn them. These simple architectural changes lead to substantial improvements in generalization on i.i.d. and even more on out-of-distribution conditions, such as image classification under natural corruptions on ImageNet-C [11] and few-shot learning on Meta-Dataset [26]. State-of-the art results are achieved on both datasets without introducing additional trainable parameters and using the default hyper-parameters of open source codebases.