DeepAI AI Chat
Log In Sign Up

Logit Clipping for Robust Learning against Label Noise

by   Hongxin Wei, et al.

In the presence of noisy labels, designing robust loss functions is critical for securing the generalization performance of deep neural networks. Cross Entropy (CE) loss has been shown to be not robust to noisy labels due to its unboundedness. To alleviate this issue, existing works typically design specialized robust losses with the symmetric condition, which usually lead to the underfitting issue. In this paper, our key idea is to induce a loss bound at the logit level, thus universally enhancing the noise robustness of existing losses. Specifically, we propose logit clipping (LogitClip), which clamps the norm of the logit vector to ensure that it is upper bounded by a constant. In this manner, CE loss equipped with our LogitClip method is effectively bounded, mitigating the overfitting to examples with noisy labels. Moreover, we present theoretical analyses to certify the noise-tolerant ability of LogitClip. Extensive experiments show that LogitClip not only significantly improves the noise robustness of CE loss, but also broadly enhances the generalization performance of popular robust losses.


page 1

page 2

page 3

page 4


Normalized Loss Functions for Deep Learning with Noisy Labels

Robust loss functions are essential for training accurate deep neural ne...

Do We Need to Penalize Variance of Losses for Learning with Label Noise?

Algorithms which minimize the averaged loss have been widely designed fo...

Curriculum Loss: Robust Learning and Generalization against Label Corruption

Generalization is vital important for many deep network models. It becom...

Learning with Noisy Labels via Sparse Regularization

Learning with noisy labels is an important and challenging task for trai...

Sample Selection with Uncertainty of Losses for Learning with Noisy Labels

In learning with noisy labels, the sample selection approach is very pop...

An Exploration into why Output Regularization Mitigates Label Noise

Label noise presents a real challenge for supervised learning algorithms...

Learning Adaptive Loss for Robust Learning with Noisy Labels

Robust loss minimization is an important strategy for handling robust le...