ASI: Accuracy-Stability Index for Evaluating Deep Learning Models

arXiv:2311.15332v2 Announce Type: replace
Abstract: In the context of deep learning research, where model introductions continually occur, the need for effective and efficient evaluation remains paramount. Existing methods often emphasize accuracy metrics, overlooking stability. To address this, the paper introduces the Accuracy-Stability Index (ASI), a quantitative measure incorporating both accuracy and stability for assessing deep learning models. Experimental results demonstrate the application of ASI, and a 3D surface model is presented for visualizing ASI, mean accuracy, and coefficient of variation. …

abstract accuracy arxiv asi context cs.ai cs.cv cs.it cs.lg cs.pf deep learning evaluation index math.it metrics paper quantitative research stability type