English

Novelty Detection via Network Saliency in Visual-based Deep Learning

Machine Learning 2019-06-11 v1 Computer Vision and Pattern Recognition Machine Learning

Abstract

Machine-learning driven safety-critical autonomous systems, such as self-driving cars, must be able to detect situations where its trained model is not able to make a trustworthy prediction. Often viewed as a black-box, it is non-obvious to determine when a model will make a safe decision and when it will make an erroneous, perhaps life-threatening one. Prior work on novelty detection deal with highly structured data and do not translate well to dynamic, real-world situations. This paper proposes a multi-step framework for the detection of novel scenarios in vision-based autonomous systems by leveraging information learned by the trained prediction model and a new image similarity metric. We demonstrate the efficacy of this method through experiments on a real-world driving dataset as well as on our in-house indoor racing environment.

Keywords

Cite

@article{arxiv.1906.03685,
  title  = {Novelty Detection via Network Saliency in Visual-based Deep Learning},
  author = {Valerie Chen and Man-Ki Yoon and Zhong Shao},
  journal= {arXiv preprint arXiv:1906.03685},
  year   = {2019}
}

Comments

To be published in Dependable and Secure Machine Learning (DSML) workshop co-located with the IEEE Conference on Dependable Systems and Networks 2019

R2 v1 2026-06-23T09:48:12.887Z