# Dual-Tree Wavelet Scattering Network with Parametric Log Transformation for Object Classification

## TL;DR

This paper presents a novel Dual-Tree Wavelet ScatterNet with parametric log transformation that enhances translation invariance and computational efficiency for object classification, outperforming existing methods on multiple datasets.

## Contribution

It introduces a new ScatterNet combining parametric log transformation with Dual-Tree wavelets, improving accuracy and efficiency over prior ScatterNet and other methods.

## Key findings

- Outperforms Mallat's ScatterNet in accuracy and efficiency
- Improves translation invariance with parametric log transformation
- Effective across various dataset sizes

## Abstract

We introduce a ScatterNet that uses a parametric log transformation with Dual-Tree complex wavelets to extract translation invariant representations from a multi-resolution image. The parametric transformation aids the OLS pruning algorithm by converting the skewed distributions into relatively mean-symmetric distributions while the Dual-Tree wavelets improve the computational efficiency of the network. The proposed network is shown to outperform Mallat's ScatterNet on two image datasets, both for classification accuracy and computational efficiency. The advantages of the proposed network over other supervised and some unsupervised methods are also presented using experiments performed on different training dataset sizes.