Benchmarking Test-Time Unsupervised Deep Neural Network Adaptation on Edge Devices

Author:

Bhardwaj Kshitij1,Diffenderfer James1,Kailkhura Bhavya1,Gokhale Maya1

Affiliation:

1. Lawrence Livermore National Laboratory,Livermore,CA

Funder

U.S. Department of Energy

Publisher

IEEE

Reference9 articles.

1. On the effectiveness of adversarial training against common corruptions;kireev;arXiv preprint arXiv 2103 05767,2021

2. Augmix: A simple data processing method to improve robustness and uncertainty;hendrycks;arXiv preprint arXiv 1912 02781,2019

3. Evaluating prediction-time batch normalization for robustness under covariate shift;nado;arXiv preprint arXiv 2006 10226,2020

4. Tent: Fully test-time adaptation by entropy minimization;wang;ICLR Spotlight,2021

5. Improving robustness against common corruptions by covariate shift adaptation;schneider;Advances in neural information processing systems,2020

Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Classification and rating of steel scrap using deep learning;Engineering Applications of Artificial Intelligence;2023-08

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3