Evaluating the Impact of Compression Techniques on the Robustness of CNNs under Natural Corruptions
评估压缩技术对CNN在自然损坏下的鲁棒性影响
机构 * Computing Institute(计算研究所) ; Federal University of Alagoas(亚拉加斯联邦大学) ; Center of Technology(技术中心) ; Federal University of Rio Grande do Norte(里奥格兰德北联邦大学)
AI总结 本文研究了压缩技术对CNN在自然损坏下的鲁棒性影响,通过量化、剪枝和权重聚类等方法,分析了鲁棒性、准确率和压缩率的权衡,发现某些压缩策略可提升鲁棒性。
Comments Accepted for publication at the 2025 International Conference on Machine Learning and Applications (ICMLA). IEEE Catalog Number: CFP25592-ART