2018 低功耗图像识别挑战赛
计算机视觉与模式识别
2018-10-04 v1
摘要
低功耗图像识别挑战赛（LPIRC，https://rebootingcomputing.ieee.org/lpirc）是始于 2015 年的年度竞赛。该竞赛旨在识别能够高效（短执行时间与低能耗）且准确（高精度）地对图像中的物体进行分类与检测的最佳技术。四年间，获胜者的分数提升了逾 24 倍。由于计算机视觉被广泛应用于诸多电池供电系统（如无人机与手机），对低功耗计算机视觉的需求将愈发重要。本文通过描述三个不同赛道及获胜者方案，对 LPIRC 2018 进行总结。
引用
@article{arxiv.1810.01732,
title = {2018 Low-Power Image Recognition Challenge},
author = {Sergei Alyamkin and Matthew Ardi and Achille Brighton and Alexander C. Berg and Yiran Chen and Hsin-Pai Cheng and Bo Chen and Zichen Fan and Chen Feng and Bo Fu and Kent Gauen and Jongkook Go and Alexander Goncharenko and Xuyang Guo and Hong Hanh Nguyen and Andrew Howard and Yuanjun Huang and Donghyun Kang and Jaeyoun Kim and Alexander Kondratyev and Seungjae Lee and Suwoong Lee and Junhyeok Lee and Zhiyu Liang and Xin Liu and Juzheng Liu and Zichao Li and Yang Lu and Yung-Hsiang Lu and Deeptanshu Malik and Eunbyung Park and Denis Repin and Tao Sheng and Liang Shen and Fei Sun and David Svitov and George K. Thiruvathukal and Baiwu Zhang and Jingchi Zhang and Xiaopeng Zhang and Shaojie Zhuo},
journal= {arXiv preprint arXiv:1810.01732},
year = {2018}
}
备注
13 pages, workshop in 2018 CVPR, competition, low-power, image recognition