Self-paced resistance learning against overfitting on noisy labels

Xiaoshuang Shi,Zhenhua Guo,Fuyong Xing,Yun Liang,Xiaofeng Zhu

Pattern Recognition（2023）

引用 3|浏览44

暂无评分

摘要

•We propose a novel resistance loss to alleviate model overfitting.•We propose a novel framework to robustly train CNNs on noisy labels.•It integrates CNNs’ memorization effect, curriculum learning with a resistance loss.

查看译文

关键词

Convolutional neural networks,Self-paced resistance,Model overfitting,Noisy labels

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要