TinyOOD: Effective out-of-Distribution Detection for TinyML

Yongchang Li; Juncheng Jia; Yan Zuo; Weipeng Zhu

ICASSP 2023accepted0 citations

TinyOOD: Effective out-of-Distribution Detection for TinyML

Yongchang Li, Juncheng Jia, Yan Zuo, Weipeng Zhu

Abstract

Tiny machine learning (TinyML) has emerged recently for resource constrained Internet of Things (IoT) devices. However, the deployed TinyML model cannot handle outof-distribution (OOD) inputs appropriately. While many high-accuracy OOD detection methods have emerged, they often ignore the limitations of the deployment environment. In this paper, we propose a novel effective out-of-distribution detection method for TinyML (TinyOOD), which exploits cascading early exit and channel-attention-based neural mean discrepancy (CA-NMD) for dynamic and efficient OOD detection on microcontroller units (MCUs). To demonstrate its effectiveness, we extensively evaluate TinyOOD using four public datasets, one as the in-distribution (ID) dataset and the others as the OOD datasets. Experiments demonstrate that TinyOOD significantly reduces the computations by up to 38.23% in inference while maintaining the performance of OOD detection.

BibTeX

@inproceedings{icassp2023_tinyoodeffective,
  title = {TinyOOD: Effective out-of-Distribution Detection for TinyML},
  author = {Yongchang Li and Juncheng Jia and Yan Zuo and Weipeng Zhu},
  booktitle = {ICASSP 2023},
  year = {2023}
}