Delving Deeper into Anti-aliasing in ConvNets

by   Xueyan Zou, et al.

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



There are no comments yet.


page 4

page 5

page 10


Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice

Vision Transformer (ViT) has recently demonstrated promise in computer v...

Adaptive feature recombination and recalibration for semantic segmentation with Fully Convolutional Networks

Fully Convolutional Networks have been achieving remarkable results in i...

On the Texture Bias for Few-Shot CNN Segmentation

Despite the initial belief that Convolutional Neural Networks (CNNs) are...

BlurNet: Defense by Filtering the Feature Maps

Recently, the field of adversarial machine learning has been garnering a...

Exploring Novel Pooling Strategies for Edge Preserved Feature Maps in Convolutional Neural Networks

With the introduction of anti-aliased convolutional neural networks (CNN...

Direction-aware Feature-level Frequency Decomposition for Single Image Deraining

We present a novel direction-aware feature-level frequency decomposition...

Code Repositories

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.