Chaotic CNN for Limited Data Image Classification

2026-04-16

AI Summary

This study addresses the degradation of generalization performance in convolutional neural networks under few-shot learning scenarios, primarily caused by overfitting and insufficient feature diversity. To mitigate these issues without increasing model complexity, the authors propose a novel feature augmentation strategy that applies nonlinear transformations—driven by chaotic systems including Logistic, skew-tent, and sine maps—to normalized feature vectors just before the classification layer. This approach reshapes the feature space to enhance class separability. Notably, it is the first to integrate multiple chaotic mappings into CNN-based feature learning. Extensive experiments on MNIST, Fashion-MNIST, and CIFAR-10 demonstrate significant improvements in classification accuracy under extremely limited training samples, with gains of up to 5.43%, 9.11%, and 7.47%, respectively, while maintaining computational efficiency and ease of integration.

Technology Category

• Machine Learning: Feature Construction/Reformulation
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• limited data
• image classification
• overfitting
• feature diversity
• CNN generalization

Innovation

• chaotic maps
• feature transformation
• limited data classification
• CNN enhancement
• nonlinear dynamics