Classification models categorize objects into given classes, guided by training samples with
input features and labels. In practice, however, labels can be corrupted by human error or …

Although data-driven fault diagnosis methods have achieved remarkable results, these
achievements often rely on high-quality datasets without noisy labels, which can mislead the …

Noisy annotations such as missing annotations and location shifts often exist in crowd
counting datasets due to multi-scale head sizes, high occlusion, etc. These noisy …

The sample selection approach is very popular in learning with noisy labels. As deep
networks “learn pattern first”, prior methods built on sample selection share a similar training …

Human-annotated vision datasets inevitably contain a fraction of human-mislabelled
examples. While the detrimental effects of such mislabelling on supervised learning are well …

Learning with noisy labels has gained increasing attention because the inevitable imperfect
labels in real-world scenarios can substantially hurt the deep model performance. Recent …

Image classification datasets exhibit a non-negligible fraction of mislabeled examples, often
due to human error when one class superficially resembles another. This issue poses …

In this paper, we propose a novel method to address the challenge of learning deep neural
network models in the presence of open-set noisy labels, which include mislabeled samples …

Existing deep learning methods often require a large amount of high-quality labeled data.
Yet, the presence of noisy labels in the real-world training data seriously affects the …

The creation of large-scale datasets annotated by humans inevitably introduces noisy
labels, leading to reduced generalization in deep-learning models. Sample selection-based …