Ting-Chun Chou, Yu-Cheng Kuo, Jhih-Yuan Huang, Wei-Po Lee
{"title":"通过对抗训练和知识提炼训练稳健图像识别模型的持续学习框架","authors":"Ting-Chun Chou, Yu-Cheng Kuo, Jhih-Yuan Huang, Wei-Po Lee","doi":"10.1080/09540091.2024.2379268","DOIUrl":null,"url":null,"abstract":"Deep learning has been widely adopted in many image recognition tasks with great success. It has now been applied to conducting tasks on vision-based edge devices with resource limitation. To secur...","PeriodicalId":50629,"journal":{"name":"Connection Science","volume":"9 1","pages":""},"PeriodicalIF":3.2000,"publicationDate":"2024-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A continual learning framework to train robust image recognition models by adversarial training and knowledge distillation\",\"authors\":\"Ting-Chun Chou, Yu-Cheng Kuo, Jhih-Yuan Huang, Wei-Po Lee\",\"doi\":\"10.1080/09540091.2024.2379268\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Deep learning has been widely adopted in many image recognition tasks with great success. It has now been applied to conducting tasks on vision-based edge devices with resource limitation. To secur...\",\"PeriodicalId\":50629,\"journal\":{\"name\":\"Connection Science\",\"volume\":\"9 1\",\"pages\":\"\"},\"PeriodicalIF\":3.2000,\"publicationDate\":\"2024-07-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Connection Science\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1080/09540091.2024.2379268\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Connection Science","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1080/09540091.2024.2379268","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
A continual learning framework to train robust image recognition models by adversarial training and knowledge distillation
Deep learning has been widely adopted in many image recognition tasks with great success. It has now been applied to conducting tasks on vision-based edge devices with resource limitation. To secur...
期刊介绍：
Connection Science is an interdisciplinary journal dedicated to exploring the convergence of the analytic and synthetic sciences, including neuroscience, computational modelling, artificial intelligence, machine learning, deep learning, Database, Big Data, quantum computing, Blockchain, Zero-Knowledge, Internet of Things, Cybersecurity, and parallel and distributed computing.
A strong focus is on the articles arising from connectionist, probabilistic, dynamical, or evolutionary approaches in aspects of Computer Science, applied applications, and systems-level computational subjects that seek to understand models in science and engineering.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
