# Delving Deeper into Anti-aliasing in ConvNets

arXiv: https://arxiv.org/abs/2008.09604 · HTML: https://mlsanity.com/paper/2008.09604/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Aug 2020.

## Built on by (most cited first, 30 of 60)

- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [Towards Stability of Autoregressive Neural Operators](https://mlsanity.com/paper/2306.10619/) (2023)
- [On Aliased Resizing and Surprising Subtleties in GAN Evaluation](https://mlsanity.com/paper/2104.11222/) (2021)
- [Frequency-aware Feature Fusion for Dense Image Prediction](https://mlsanity.com/paper/2408.12879/) (2024)
- [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)
- [Deep networks for system identification: a Survey](https://mlsanity.com/paper/2301.12832/) (2023)
- [Frequency-Adaptive Dilated Convolution for Semantic Segmentation](https://mlsanity.com/paper/2403.05369/) (2024)
- [FrequencyLowCut Pooling -- Plug & Play against Catastrophic Overfitting](https://mlsanity.com/paper/2204.00491/) (2022)
- [Adaptive Dynamic Filtering Network for Image Denoising](https://mlsanity.com/paper/2211.12051/) (2022)
- [Impact of Aliasing on Generalization in Deep Convolutional Networks](https://mlsanity.com/paper/2108.03489/) (2021)
- [Learnable Polyphase Sampling for Shift Invariant and Equivariant Convolutional Networks](https://mlsanity.com/paper/2210.08001/) (2022)
- [Seeing the Unseen: A Frequency Prompt Guided Transformer for Image Restoration](https://mlsanity.com/paper/2404.00288/) (2024)
- [Blending Anti-Aliasing into Vision Transformer](https://mlsanity.com/paper/2110.15156/) (2021)
- [Making Vision Transformers Truly Shift-Equivariant](https://mlsanity.com/paper/2305.16316/) (2023)
- [Blurs Behave Like Ensembles: Spatial Smoothings to Improve Accuracy, Uncertainty, and Robustness](https://mlsanity.com/paper/2105.12639/) (2021)
- [Global Pooling, More than Meets the Eye: Position Information is Encoded Channel-Wise in CNNs](https://mlsanity.com/paper/2108.07884/) (2021)
- [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)
- [Alias-Free Convnets: Fractional Shift Invariance via Polynomial Activations](https://mlsanity.com/paper/2303.08085/) (2023)
- [How Convolutional Neural Networks Deal with Aliasing](https://mlsanity.com/paper/2102.07757/) (2021)
- [Truly shift-equivariant convolutional neural networks with adaptive polyphase upsampling](https://mlsanity.com/paper/2105.04040/) (2021)
- [When Semantic Segmentation Meets Frequency Aliasing](https://mlsanity.com/paper/2403.09065/) (2024)
- [Boosting Night-time Scene Parsing with Learnable Frequency](https://mlsanity.com/paper/2208.14241/) (2022)
- [Improving Feature Stability during Upsampling -- Spectral Artifacts and the Importance of Spatial Context](https://mlsanity.com/paper/2311.17524/) (2023)
- [Investigating Shift Equivalence of Convolutional Neural Networks in Industrial Defect Segmentation](https://mlsanity.com/paper/2309.16902/) (2023)
- [Improving Shift Invariance in Convolutional Neural Networks with Translation Invariant Polyphase Sampling](https://mlsanity.com/paper/2404.07410/) (2024)
- [Beware of Aliases -- Signal Preservation is Crucial for Robust Image Restoration](https://mlsanity.com/paper/2406.07435/) (2024)
- [Depth Super-Resolution from Explicit and Implicit High-Frequency Features](https://mlsanity.com/paper/2303.09307/) (2023)
- [PRUE: A Practical Recipe for Field Boundary Segmentation at Scale](https://mlsanity.com/paper/2603.27101/) (2026)

## Abstract (arXiv)

Aliasing refers to the phenomenon that high frequency signals degenerate into completely different ones after sampling. It arises as a problem in the context of deep learning as downsampling layers are widely adopted in deep architectures to reduce parameters and computation. The standard solution is to apply a low-pass filter (e.g., Gaussian blur) before downsampling. However, it can be suboptimal to apply the same filter across the entire content, as the frequency of feature maps can vary across both spatial locations and feature channels. To tackle this, we propose an adaptive content-aware low-pass filtering layer, which predicts separate filter weights for each spatial location and channel group of the input feature maps. We investigate the effectiveness and generalization of the proposed method across multiple tasks including ImageNet classification, COCO instance segmentation, and Cityscapes semantic segmentation. Qualitative and quantitative results demonstrate that our approach effectively adapts to the different feature frequencies to avoid aliasing while preserving useful information for recognition. Code is available at https://maureenzou.github.io/ddac/.