Delving Deeper into Anti-Aliasing in ConvNets

BMVC(2022)

引用 83|浏览87
暂无评分
摘要
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 (Zhang in: ICML, 2020). 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 image classification, semantic segmentation, instance segmentation, video instance segmentation, and image-to-image translation. Both 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/ .
更多
查看译文
关键词
Computer vision,Anti-aliasing,Neural network consistency,Neural network architecture
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要