Chaotic CNN for Limited Data Image Classification

TL;DR

This paper introduces a chaos-based feature transformation for CNNs that improves image classification performance in limited data scenarios without increasing model complexity.

Contribution

It proposes a simple, nonlinear chaos-inspired method to reshape feature space, enhancing class separability and accuracy in CNNs with minimal computational overhead.

Findings

Maximum 5.43% accuracy gain on MNIST with skew tent map at 40 samples/class.

Up to 9.11% improvement on Fashion-MNIST with sine map at 50 samples/class.

7.47% gain on CIFAR-10 with skew tent map at 200 samples/class.

Abstract

Convolutional neural networks (CNNs) often exhibit poor generalisation in limited training data scenarios due to overfitting and insufficient feature diversity. In this work, a simple and effective chaos-based feature transformation is proposed to enhance CNN performance without increasing model complexity. The method applies nonlinear transformations using logistic, skew tent, and sine maps to normalised feature vectors before the classification layer, thereby reshaping the feature space and improving class separability. The approach is evaluated on greyscale datasets (MNIST and Fashion-MNIST) and an RGB dataset (CIFAR-10) using CNN architectures of varying depth under limited data conditions. The results show consistent improvement over the standalone (SA) CNN across all datasets. Notably, a maximum performance gain of 5.43% is achieved on MNIST using the skew tent map with a 3-layer CNN at 40 samples per class. A higher gain of 9.11% is observed on Fashion-MNIST using the sine map with a 3-layer CNN at 50 samples per class. Additionally, a strong gain of 7.47% is obtained on CIFAR-10 using the skew tent map at 200 samples per class. The consistent improvements across different chaotic maps indicate that the performance gain is driven by the shared nonlinear and dynamical properties of chaotic systems. The proposed method is computationally efficient, requires no additional trainable parameters, and can be easily integrated into existing CNN architectures, making it a practical solution for data-scarce image classification tasks.