Chaotic Contrastive Learning for Robust Texture Classification

TL;DR

This paper presents a novel chaotic contrastive learning framework that enhances texture classification robustness by integrating chaotic maps as data augmentation and combining multi-level features, outperforming existing methods.

Contribution

The paper introduces a new chaotic contrastive pre-training strategy using Logistic, Tent, and Sine maps for data augmentation in texture classification.

Findings

Outperforms state-of-the-art on six texture benchmarks.

Achieves higher accuracy across all tested datasets.

Demonstrates robustness to environmental variations.

Abstract

Texture classification is a pivotal task in computer vision, presenting unique challenges due to high inter-class similarity and the sensitivity of structural patterns to scale and illumination changes. While Convolutional Neural Networks (CNNs) and recent Vision Transformers have set performance benchmarks, they often require extensive labeled datasets or struggle to generalize across domains due to an over-reliance on color and shape features. This paper introduces a novel framework that synergizes Self-Supervised Learning (SSL) with deterministic chaotic dynamics. We propose a chaotic contrastive pre-training strategy, where pixel-wise chaotic maps, specifically Logistic, Tent, and Sine maps, act as non-linear data augmentation techniques. These chaotic perturbations, grounded in ergodic theory, force the network to learn topologically robust features by mimicking complex environmental noise and reflectance variations. Furthermore, we introduce an attention-based feature ensemble that fuses high-level semantic representations from a supervised large backbone with low-frequency structural features from a chaos-pretrained tiny encoder. Experimental results on six texture benchmarks (FMD, UMD, KTH-TIPS2-b, DTD, GTOS, and 1200Tex) demonstrate the superiority of the proposed method, outperforming state-of-the-art approaches and achieving promising accuracies on all the analyzed datasets.