DiTMoS: Delving into Diverse Tiny-Model Selection on Microcontrollers

arXiv:2403.09035v1 Announce Type: new
Abstract: Enabling efficient and accurate deep neural network (DNN) inference on microcontrollers is non-trivial due to the constrained on-chip resources. Current methodologies primarily focus on compressing larger models yet at the expense of model accuracy. In this paper, we rethink the problem from the inverse perspective by constructing small/weak models directly and improving their accuracy. Thus, we introduce DiTMoS, a novel DNN training and inference framework with a selector-classifiers architecture, where the selector routes each input …

abstract accuracy arxiv chip cs.lg current deep neural network diverse dnn enabling focus inference larger models microcontrollers model accuracy model selection network neural network paper perspective resources type