Multi-Path Learnable Wavelet Neural Network for Image Classification

TL;DR

This paper introduces a multi-path wavelet neural network for image classification that significantly reduces the number of trainable parameters while maintaining high accuracy, by using learnable wavelet decompositions in parallel.

Contribution

It presents a novel multi-path wavelet neural network architecture with learnable wavelet decompositions, enabling fewer parameters without sacrificing performance.

Findings

Parameter count is significantly reduced.

Comparable accuracy to traditional deep models.

Effective on standard image datasets.

Abstract

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.