Which Strategies Matter for Noisy Label Classification? Insight into Loss and Uncertainty

by   Wonyoung Shin, et al.

Label noise is a critical factor that degrades the generalization performance of deep neural networks, thus leading to severe issues in real-world problems. Existing studies have employed strategies based on either loss or uncertainty to address noisy labels, and ironically some strategies contradict each other: emphasizing or discarding uncertain samples or concentrating on high or low loss samples. To elucidate how opposing strategies can enhance model performance and offer insights into training with noisy labels, we present analytical results on how loss and uncertainty values of samples change throughout the training process. From the in-depth analysis, we design a new robust training method that emphasizes clean and informative samples, while minimizing the influence of noise using both loss and uncertainty. We demonstrate the effectiveness of our method with extensive experiments on synthetic and real-world datasets for various deep learning models. The results show that our method significantly outperforms other state-of-the-art methods and can be used generally regardless of neural network architectures.


page 2

page 4

page 5

page 6

page 7

page 8

page 9

page 10


Uncertainty-Aware Learning Against Label Noise on Imbalanced Datasets

Learning against label noise is a vital topic to guarantee a reliable pe...

PARS: Pseudo-Label Aware Robust Sample Selection for Learning with Noisy Labels

Acquiring accurate labels on large-scale datasets is both time consuming...

Tripartite: Tackle Noisy Labels by a More Precise Partition

Samples in large-scale datasets may be mislabeled due to various reasons...

GMM Discriminant Analysis with Noisy Label for Each Class

Real world datasets often contain noisy labels, and learning from such d...

Two-Phase Learning for Overcoming Noisy Labels

To counter the challenge associated with noise labels, the learning stra...

Unsupervised Data Uncertainty Learning in Visual Retrieval Systems

We introduce an unsupervised formulation to estimate heteroscedastic unc...

Confidence Adaptive Regularization for Deep Learning with Noisy Labels

Recent studies on the memorization effects of deep neural networks on no...