Efficient LWPooling: Rethinking the Wavelet Pooling for Scene Parsing

作者：Yuting Yang, Licheng Jiao, Xu Liu, Lingling Li, Fang Liu, Shuyuan Yang, Xiangrong Zhang · 发表于：IEEE Transactions on Circuits and Systems for Video Technology · 年份：2024 · DOI：10.1109/tcsvt.2024.3383072 · 被引用次数：9 · 研究领域：Image Retrieval and Classification Techniques、Advanced Image and Video Retrieval Techniques、Video Analysis and Summarization

Existing wavelet pooling methods discard the high-frequency sub-bands, which can improve the noise-robustness of convolutional neural networks (CNNs) but lose the essential detailed features. Besides, most of them depend on different wavelets, which is not adaptive. In this paper, a novel efficient lifting-based wavelet pooling (LWPooling) is proposed to alleviate the problems above. Firstly, wavelet pooling is rethought based on the equivalence of 2D discrete wavelet transform (DWT) and standard average pooling (SAP), which suggests the lack of detailed information on traditional wavelet pooling. Secondly, the efficient LWPooling module is proposed to adaptively capture and preserve the critical high-frequency features via lifting-based wavelets. It can constrain the features linear independence, which efficiently makes important features salient. Thirdly, the lifting-based wavelet collaborative network (LWCNet) is constructed for classification and segmentation tasks based on the efficient LWPooling module. Experiments are validated on Cifar10, Cifar100, and ADE20K datasets. It suggests that the efficient LWPooling can enhance CNN’s representation and achieve a particular performance advantage compared to average, maximum, and original wavelet pooling. Besides, the proposed LWCNet shows the potential for scene parsing. The code implementation will be available at https://github.com/yutinyang/LWCNet.