Is Haar Enough? Exploring Symlets and Coiflets for Wavelet Convolution Layers

2026-08-18

AI Summary

研究探讨了Symlets和Coiflets在波浪卷积层中的应用，通过调整滤波器长度与分解层数的平衡来减少参数量和计算量，以提高图像分类和语义分割任务的效率。

Abstract

Wavelet convolution layers have recently emerged as an efficient mechanism for enlarging receptive fields through multiresolution analysis, but prior work has fixed the wavelet basis to Haar or Daubechies at a chosen decomposition depth, leaving open whether a different basis can shift the underlying efficiency frontier. We identify and characterize a previously unexplored trade-off in this setting: bases with stronger approximation properties (longer filters) can reduce the decomposition depth required for competitive accuracy, yielding a net reduction in parameters and FLOPs despite higher perlevel transform cost. We formalize this as an F-vs.-L tradeoff (filter length vs. decomposition levels) and study it systematically across Haar, Daubechies, Symlets, and Coiflets under controlled architectures and budgets. On image classification (CIFAR-10, ImageNet-1K) and semantic segmentation (Cityscapes), Coiflet-based wavelet convolutions match Haar at deeper levels with approximately 32% fewer additional parameters and 33% fewer additional FLOPs, providing a concrete and actionable design choice for practitioners building wavelet-based architectures.

Problem

• Wavelet Convolution
• Basis Selection
• Efficiency Frontier
• Parameter Reduction
• FLOPs

Innovation

• Wavelet Convolution
• Multiresolution Analysis
• Filter Length vs. Decomposition Levels Trade-off
• Coiflets
• Parameter Reduction