Existing studies indicate that deep neural networks (DNNs) can eventually memorize the
label noise. We observe that the memorization strength of DNNs towards each instance is …

The sample selection approach is popular in learning with noisy labels. The state-of-the-art
methods train two deep networks simultaneously for sample selection, which aims to employ …

There has been significant attention devoted to the effectiveness of various domains, such
as semi-supervised learning, contrastive learning, and meta-learning, in enhancing the …

Learning from crowds describes that the annotations of training data are obtained with
crowd-sourcing services. Multiple annotators each complete their own small part of the …

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 …

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 …

Abstract Dynamic Digital Humans (DDHs) refer to 3D digital models that are animated using
predefined motions. However, these models are susceptible to noise and shift distortions …

Fatigue is a significant safety concern across various domains, and accurate detection is
vital. However, the commonly employed fine-grained labels (seconds-based) frequently …

Federated learning (FL) is a promising decentralized machine learning approach that
enables multiple distributed clients to train a model jointly while keeping their data private …

Due to issues with sample quality, there is an increasing interest in deep learning models
that can handle noisy labels. Currently, the optimal way to deal with noisy labels is by …