Combating Noisy Labels through Fostering Self- and Neighbor-Consistency
通过促进自一致性与邻居一致性来对抗噪声标签
机构 * School of Computer Science and Engineering, Nanjing University of Science and Technology(南京理工大学计算机科学与工程学院) ; State Key Laboratory of Intelligent Manufacturing of Advanced Construction Machinery(先进施工机械智能制造国家重点实验室) ; School of Computer Science, Faculty of Engineering, the University of Sydney(悉尼大学工程学院计算机科学系) ; School of Computer Science and Engineering, University of Electronic Science and Technology of China(电子科技大学计算机科学与工程学院)
AI总结 本文提出Jo-SNC方法,通过自一致性与邻居一致性提升模型对噪声标签的鲁棒性,结合自适应阈值和三元组正则化,有效识别并处理分布内和分布外噪声样本。
Comments accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence