CrossSplit: Mitigating Label Noise Memorization through Data Splitting

by   Jihye Kim, et al.

We approach the problem of improving robustness of deep learning algorithms in the presence of label noise. Building upon existing label correction and co-teaching methods, we propose a novel training procedure to mitigate the memorization of noisy labels, called CrossSplit, which uses a pair of neural networks trained on two disjoint parts of the dataset. CrossSplit combines two main ingredients: (i) Cross-split label correction. The idea is that, since the model trained on one part of the data cannot memorize example-label pairs from the other part, the training labels presented to each network can be smoothly adjusted by using the predictions of its peer network; (ii) Cross-split semi-supervised training. A network trained on one part of the data also uses the unlabeled inputs of the other part. Extensive experiments on CIFAR-10, CIFAR-100, Tiny-ImageNet and mini-WebVision datasets demonstrate that our method can outperform the current state-of-the-art up to 90


Robust Temporal Ensembling for Learning with Noisy Labels

Successful training of deep neural networks with noisy labels is an esse...

SplitNet: Learnable Clean-Noisy Label Splitting for Learning with Noisy Labels

Annotating the dataset with high-quality labels is crucial for performan...

Unsupervised label noise modeling and loss correction

Despite being robust to small amounts of label noise, convolutional neur...

Consistency Regularization Can Improve Robustness to Label Noise

Consistency regularization is a commonly-used technique for semi-supervi...

How Does Disagreement Benefit Co-teaching?

Learning with noisy labels is one of the most important question in weak...

Learning with Neighbor Consistency for Noisy Labels

Recent advances in deep learning have relied on large, labelled datasets...

Robust Deep Learning with Active Noise Cancellation for Spatial Computing

This paper proposes CANC, a Co-teaching Active Noise Cancellation method...

Please sign up or login with your details

Forgot password? Click here to reset