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

IF 3.2 4区计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Connection Science Pub Date : 2024-07-20 DOI:10.1080/09540091.2024.2379268

Ting-Chun Chou, Yu-Cheng Kuo, Jhih-Yuan Huang, Wei-Po Lee

引用次数: 0

摘要

深度学习已被广泛应用于许多图像识别任务，并取得了巨大成功。现在，它已被应用于在资源有限的基于视觉的边缘设备上执行任务。为了确保边缘设备的安全，我们需要...

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

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...

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Connection Science 工程技术-计算机：理论方法

CiteScore

6.50

自引率

39.60%

发文量

审稿时长

3 months

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.