Cascaded Classifier for Pareto-Optimal Accuracy-Cost Trade-Off Using off-the-Shelf ANNs
This work addresses cost-efficiency for users of state-of-the-art classifiers, offering a method to optimize accuracy-cost trade-offs, though it is incremental as it builds on existing cascaded classifier concepts.
The paper tackles the problem of reducing computational cost in machine learning classifiers while maintaining accuracy, by analyzing optimal pass-on criteria for cascaded classifiers and deriving a methodology that achieves a 1.32x cost reduction without accuracy loss and scales cost over two orders with graceful accuracy degradation.
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 1.32x 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.