Frequency-Dividing Downsampling Module of the Lifting Scheme for Image Classification
Zhichao Wang, Zishan Shi, Dingwen Wang, Chu He · 2022 IEEE International Conference on Multimedia and Expo (ICME) · 2022
Convolutional neural networks(CNNs) currently dominate the field of computer vision, where the pooling layer plays an important role in reducing computational effort and avoiding overfitting. However, the commonly used methods do not design the pooling layer from the perspective of frequency. In this paper, we propose a Lifting Scheme-based frequency-dividing downsampling framework and describe a pooling layer called frequency-dividing pooling (FDP). The two branches of the Lifting Scheme process the images by frequency, which not only enhances the interpretability of the neural network but also improves the classification accuracy of the neural network. We conduct experiments on three standard datasets and the results all demonstrate that our proposed FDP is effective.