# How Convolutional Neural Networks Deal with Aliasing

arXiv: https://arxiv.org/abs/2102.07757 · HTML: https://mlsanity.com/paper/2102.07757/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 17 references that are in the map.
- First posted on arXiv 15 Feb 2021.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Making Convolutional Networks Shift-Invariant Again](https://mlsanity.com/paper/1904.11486/) (2019)
- [Why do deep convolutional networks generalize so poorly to small image transformations?](https://mlsanity.com/paper/1805.12177/) (2018)
- [Delving Deeper into Anti-aliasing in ConvNets](https://mlsanity.com/paper/2008.09604/) (2020)
- [An Effective Anti-Aliasing Approach for Residual Networks](https://mlsanity.com/paper/2011.10675/) (2020)
- [Geodesics of learned representations](https://mlsanity.com/paper/1511.06394/) (2015)
- [WaveCycleGAN2: Time-domain Neural Post-filter for Speech Waveform Generation](https://mlsanity.com/paper/1904.02892/) (2019)

## Built on by (most cited first, 10 of 10)

- [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)
- [Deep networks for system identification: a Survey](https://mlsanity.com/paper/2301.12832/) (2023)
- [Learning strides in convolutional neural networks](https://mlsanity.com/paper/2202.01653/) (2022)
- [Aliasing is a Driver of Adversarial Attacks](https://mlsanity.com/paper/2212.11760/) (2022)
- [A New Multimodal Medical Image Fusion based on Laplacian Autoencoder with Channel Attention](https://mlsanity.com/paper/2310.11896/) (2023)
- [SUPER Module for Detail-Sensitive and Cost-Efficient U-Net Variant Decoders](https://mlsanity.com/paper/2511.11015/) (2025)
- [SOMA: Feature Gradient Enhanced Affine-Flow Matching for SAR-Optical Registration](https://mlsanity.com/paper/2511.13168/) (2025)
- [DLink: Distilling Layer-wise and Dominant Knowledge from EEG Foundation Models](https://mlsanity.com/paper/2604.15016/) (2026)
- [Resolution Allocation with Learnable Resizing and Spectral Filter Parameterization](https://mlsanity.com/paper/2610.20274/) (2026)

## Abstract (arXiv)

The convolutional neural network (CNN) remains an essential tool in solving computer vision problems. Standard convolutional architectures consist of stacked layers of operations that progressively downscale the image. Aliasing is a well-known side-effect of downsampling that may take place: it causes high-frequency components of the original signal to become indistinguishable from its low-frequency components. While downsampling takes place in the max-pooling layers or in the strided-convolutions in these models, there is no explicit mechanism that prevents aliasing from taking place in these layers. Due to the impressive performance of these models, it is natural to suspect that they, somehow, implicitly deal with this distortion. The question we aim to answer in this paper is simply: "how and to what extent do CNNs counteract aliasing?" We explore the question by means of two examples: In the first, we assess the CNNs capability of distinguishing oscillations at the input, showing that the redundancies in the intermediate channels play an important role in succeeding at the task; In the second, we show that an image classifier CNN while, in principle, capable of implementing anti-aliasing filters, does not prevent aliasing from taking place in the intermediate layers.