Corruption Robustness Analysis of Radar Micro-Doppler Classification for Human Activity Recognition-Reference-Cited by-同舟云学术

Corruption Robustness Analysis of Radar Micro-Doppler Classification for Human Activity Recognition

Author:

Zhou Yi¹^ORCID,Yu Xuliang²,López-Benítez Miguel³^ORCID,Yu Limin⁴^ORCID,Yue Yutao⁵^ORCID

Affiliation:

1. Institute of Deep Perception Technology, Jiangsu Industrial Technology Research Institute (JITRI), Wuxi, China

2. College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China

3. Department of Electrical Engineering and Electronics, University of Liverpool, Liverpool, U.K.

4. Department of Electrical and Electronic Engineering, School of Advanced Technology, Xi’an Jiaotong-Liverpool University, Suzhou, China

5. Thrust of Artificial Intelligence and the Thrust of Intelligent Transportation, The Hong Kong University and Technology, Guangzhou, China

Funder

Jiangsu Industrial Technology Research Institute

Wuxi National Hi-Tech District

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Link

Reference40 articles.

1. Benchmarking neural network robustness to common corruptions and perturbations;Hendrycks;arXiv:1903.12261,2019

2. RobustART: Benchmarking robustness on architecture design and training techniques;Tang;arXiv:2109.05211,2021

3. Robustness may be at odds with accuracy;Tsipras;arXiv:1805.12152,2018

4. Understanding and mitigating the tradeoff between robustness and accuracy;Raghunathan;arXiv:2002.10716,2020

5. Benchmarking the robustness of spatial–temporal models against corruptions;Yi;arXiv:2110.06513,2021