no code implementations • 2 May 2024 • Zijia Wang, Wenbin Yang, ZhiSong Liu, Zhen Jia
Training deep neural networks (DNNs) from noisy labels is an important and challenging task.
no code implementations • 2 May 2024 • Zijia Wang, Wenbin Yang, ZhiSong Liu, Zhen Jia
Specifically, we propose to use Expectation-Maximization (EM) to smooth the labels and comprehensively estimate the uncertainty information.