An Optimized Toolbox for Advanced Image Processing with Tsetlin Machine Composites

2024-06-02

arXiv.org

AI Summary

To address the low classification accuracy of Tsetlin Machines (TMs) on color image datasets—particularly CIFAR-10—this paper introduces TM Composites, the first dedicated toolbox for image analysis based on TMs. Methodologically, it systematically integrates seven domain-specific image feature extraction modules—including Canny edge detection, Histogram of Oriented Gradients (HOG), adaptive/Gaussian/Otsu thresholding, and color thermometers—combined with Bayesian hyperparameter optimization. The contributions are twofold: (1) establishing the TM Composites paradigm for interpretable, feature-driven image analysis using TMs; and (2) achieving a new state-of-the-art test accuracy of 82.8% on CIFAR-10, surpassing the previous best TM-based result by 7.7 percentage points (from 75.1% in 2023). This advance demonstrates significant progress in enhancing TM performance for complex color image classification while preserving interpretability and computational efficiency.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Interpretability, Explainability, and Transparency
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

The Tsetlin Machine (TM) has achieved competitive results on several image classification benchmarks, including MNIST, K-MNIST, F-MNIST, and CIFAR-2. However, color image classification is arguably still in its infancy for TMs, with CIFAR-10 being a focal point for tracking progress. Over the past few years, TM's CIFAR-10 accuracy has increased from around 61% in 2020 to 75.1% in 2023 with the introduction of Drop Clause. In this paper, we leverage the recently proposed TM Composites architecture and introduce a range of TM Specialists that use various image processing techniques. These include Canny edge detection, Histogram of Oriented Gradients, adaptive mean thresholding, adaptive Gaussian thresholding, Otsu's thresholding, color thermometers, and adaptive color thermometers. In addition, we conduct a rigorous hyperparameter search, where we uncover optimal hyperparameters for several of the TM Specialists. The result is a toolbox that provides new state-of-the-art results on CIFAR-10 for TMs with an accuracy of 82.8%. In conclusion, our toolbox of TM Specialists forms a foundation for new TM applications and a landmark for further research on TM Composites in image analysis.

Problem

• Enhancing color image classification accuracy
• Optimizing Tsetlin Machine Composites architecture
• Developing advanced image processing techniques

Innovation

• TM Composites enhance image processing.
• Specialists utilize advanced thresholding techniques.
• Hyperparameter optimization improves accuracy.