Delving Deeper into Anti-aliasing in ConvNets

TL;DR

This paper introduces an adaptive, content-aware low-pass filtering layer for ConvNets that dynamically adjusts to local feature frequencies, reducing aliasing and improving performance across various vision tasks.

Contribution

It proposes a novel adaptive filtering method that predicts separate filter weights for each spatial location and channel, enhancing anti-aliasing in deep neural networks.

Findings

Improves accuracy on ImageNet classification.

Enhances segmentation performance on COCO and Cityscapes.

Effectively reduces aliasing while preserving useful features.

Abstract

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/.