An Effective Anti-Aliasing Approach for Residual Networks

TL;DR

This paper introduces a simple yet effective architectural modification for residual networks that mitigates frequency aliasing, leading to improved out-of-distribution generalization without increasing model complexity.

Contribution

The authors propose using non-trainable blur filters and smooth activations at key network points to reduce aliasing effects in residual networks.

Findings

Significant improvement in ImageNet-C classification accuracy.

Enhanced few-shot learning performance on Meta-Dataset.

No additional trainable parameters or hyper-parameter tuning required.

Abstract

Image pre-processing in the frequency domain has traditionally played a vital role in computer vision and was even part of the standard pipeline in the early days of deep learning. However, with the advent of large datasets, many practitioners concluded that this was unnecessary due to the belief that these priors can be learned from the data itself. Frequency aliasing is a phenomenon that may occur when sub-sampling any signal, such as an image or feature map, causing distortion in the sub-sampled output. We show that we can mitigate this effect by placing non-trainable blur filters and using smooth activation functions at key locations, particularly where networks lack the capacity to learn them. These simple architectural changes lead to substantial improvements in out-of-distribution generalization on both image classification under natural corruptions on ImageNet-C [10] and few-shot learning on Meta-Dataset [17], without introducing additional trainable parameters and using the default hyper-parameters of open source codebases.