Log In Sign Up

Learning to Combat Noisy Labels via Classification Margins

by   Jason Z. Lin, et al.

A deep neural network trained on noisy labels is known to quickly lose its power to discriminate clean instances from noisy ones. After the early learning phase has ended, the network memorizes the noisy instances, which leads to a degradation in generalization performance. To resolve this issue, we propose MARVEL (MARgins Via Early Learning), where we track the goodness of "fit" for every instance by maintaining an epoch-history of its classification margins. Based on consecutive negative margins, we discard suspected noisy instances by zeroing out their weights. In addition, MARVEL+ upweights arduous instances enabling the network to learn a more nuanced representation of the classification boundary. Experimental results on benchmark datasets with synthetic label noise show that MARVEL outperforms other baselines consistently across different noise levels, with a significantly larger margin under asymmetric noise.


page 1

page 2

page 3

page 4


Class2Simi: A New Perspective on Learning with Label Noise

Label noise is ubiquitous in the era of big data. Deep learning algorith...

Truncate-Split-Contrast: A Framework for Learning from Mislabeled Videos

Learning with noisy label (LNL) is a classic problem that has been exten...

Leveraging inductive bias of neural networks for learning without explicit human annotations

Classification problems today are typically solved by first collecting e...

Learning with Label Noise for Image Retrieval by Selecting Interactions

Learning with noisy labels is an active research area for image classifi...

Regularizing Neural Network Training via Identity-wise Discriminative Feature Suppression

It is well-known that a deep neural network has a strong fitting capabil...

Memorization-Dilation: Modeling Neural Collapse Under Noise

The notion of neural collapse refers to several emergent phenomena that ...

Early-Learning Regularization Prevents Memorization of Noisy Labels

We propose a novel framework to perform classification via deep learning...