“How many images do I need?” Understanding how sample size per class affects deep learning model performance metrics for balanced designs in autonomous wildlife monitoring

Author:

Shahinfar Saleh,Meek Paul,Falzon Greg

Funder

Department of Agriculture and Water Resources, Australian Government

Publisher

Elsevier BV

Subject

Applied Mathematics,Computational Theory and Mathematics,Computer Science Applications,Ecological Modeling,Modeling and Simulation,Ecology,Ecology, Evolution, Behavior and Systematics

Reference42 articles.

1. Deep Learning on Small Datasets without Pre-Training Using Cosine Loss;Barz,2020

2. Recognition in Terra Incognita;Beery,2018

3. Synthetic examples improve generalization for rare classes;Beery,2020

4. How Much Data is Needed to Train a Medical Image Deep Learning System to Achieve Necessary High Accuracy?;Cho,2016

5. Making inference with messy (citizen science) data: when are data accurate enough and how can they be improved?;Clare;Ecol. Appl.,2019

Cited by 108 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

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