Year: 2022
Type: preprint
Abstract: Deep neural networks trained with standard cross-entropy loss are more prone to memorize noisy labels, which degrades their performance. Negative learning using complementary labels is more robust when noisy labels intervene but with an extremely slow model convergence speed. In this paper, we first introduce a bidirectional learning scheme, where positive learning ensures convergence speed while negative learning robustly copes with label noise. Further, a dynamic sample reweighting strategy is proposed to globally weaken the effect of noise-labeled samples by exploiting the excellent discriminatory ability of negative learning on the sample probability distribution. In addition, we combine self-distillation to further improve the model performance. The code is available at \url{https://github.com/chenchenzong/BLDR}.
Source: arXiv (Cornell University)
Authors: Zong, Chen-Chen, Cao, Zheng-Tao, Guo, Hong-Tao, Du, Yun, Xie, Ming-Kun, Li, Shao-Yuan, Huang, Sheng-Jun
Institution: Nanjing University of Aeronautics and Astronautics
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4297630647