Multi-Path Learnable Wavelet Neural Network for Image Classification
This addresses the computational efficiency issue for researchers and practitioners in computer vision, though it appears incremental as it builds on existing wavelet and neural network techniques.
The paper tackles the problem of large parameter counts in deep neural networks for image classification by proposing a multi-path wavelet neural network architecture, achieving comparable accuracy with significantly fewer parameters on common image datasets.
Despite the remarkable success of deep learning in pattern recognition, deep network models face the problem of training a large number of parameters. In this paper, we propose and evaluate a novel multi-path wavelet neural network architecture for image classification with far less number of trainable parameters. The model architecture consists of a multi-path layout with several levels of wavelet decompositions performed in parallel followed by fully connected layers. These decomposition operations comprise wavelet neurons with learnable parameters, which are updated during the training phase using the back-propagation algorithm. We evaluate the performance of the introduced network using common image datasets without data augmentation except for SVHN and compare the results with influential deep learning models. Our findings support the possibility of reducing the number of parameters significantly in deep neural networks without compromising its accuracy.