Cascaded Classifier for Pareto-Optimal Accuracy-Cost Trade-Off Using Off-the-Shelf ANNs

• Published in: Machine Learning, Optimization, and Data Science Vol. 13164; pp. 423 - 435
• Main Authors: Latotzke, Cecilia, Loh, Johnson, Gemmeke, Tobias
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2022; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Cascaded classifier; Design methodology; Edge devices; Machine learning; Pareto analysis; Preliminary classifier
• ISBN: 3030954692; 9783030954697
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-030-95470-3_32

Machine-learning classifiers provide high quality of service in classification tasks. Research now targets cost reduction measured in terms of average processing time or energy per solution. Revisiting the concept of cascaded classifiers, we present a first of its kind analysis of optimal pass-on criteria between the classifier stages. Based on this analysis, we derive a methodology to maximize accuracy and efficiency of cascaded classifiers. On the one hand, our methodology allows cost reduction of 1.32×\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\times $$\end{document} while preserving reference classifier’s accuracy. On the other hand, it allows to scale cost over two orders while gracefully degrading accuracy. Thereby, the final classifier stage sets the top accuracy. Hence, the multi-stage realization can be employed to optimize any state-of-the-art classifier.