Haar wavelet downsampling: A simple but effective downsampling module for semantic segmentation

Guoping Xu, Wentao Liao, Xuan Zhang, Chang Li, Xinwei He, Xinglong Wu

Abstract: Highlights•We propose a novel Wavelet-based downsampling module (HWD) for CNNs. To the best of our knowledge, our method is the first attempt to explore feasibility by prohibiting (impeding) information loss in the downsampling stage of DCNNs for the semantic segmentation task.•We explore the measurement of information uncertainty across layers in CNNs, and propose a novel metric, named Feature Entropy Index (FEI), to evaluate the information uncertainty or feature importance between the downsampled feature maps and the prediction results.•The proposed HWD can be directly replaced the strided convolution or pooling layer without significant increase of computation overhead and be easily integrated into the current segmentation architectures. Comprehensive experiments demonstrate the effectiveness of the HWD module when comparing with seven state-of-the-art segmentation methods.