The existence of noisy labels in real-world data negatively impacts the performance of deep
learning models. Although much research effort has been devoted to improving robustness …

Label noise significantly degrades the generalization ability of deep models in applications.
Effective strategies and approaches (eg, re-weighting or loss correction) are designed to …

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 …

Existing works on anomaly detection (AD) rely on clean labels from human annotators that
are expensive to acquire in practice. In this work, we propose a method to leverage …

Deep models trained with noisy labels are prone to over-fitting and struggle in
generalization. Most existing solutions are based on an ideal assumption that the label …

Collecting large-scale datasets is crucial for training deep models, annotating the data,
however, inevitably yields noisy labels, which poses challenges to deep learning algorithms …

Movie highlights stand out of the screenplay for efficient browsing and play a crucial role on
social media platforms. Based on existing efforts, this work has two observations:(1) For …

Machine learning-guided protein engineering is rapidly progressing; however, collecting
high-quality, large datasets remains a bottleneck. Directed evolution and protein …

In label-noise learning, estimating the transition matrix is a hot topic as the matrix plays an
important role in building statistically consistent classifiers. Traditionally, the transition from …

Weakly supervised learning is a popular approach for training machine learning models in
low-resource settings. Instead of requesting high-quality yet costly human annotations, it …