Source free domain adaptation (SFDA) aims to transfer a trained source model to the
unlabeled target domain without accessing the source data. However, the SFDA setting …

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 …

Multi-label classification poses challenges due to imbalanced and noisy labels in training
data. In this paper, we propose a unified data augmentation method, named BalanceMix, to …

Classification is a fundamental task in science and engineering on which machine learning
methods have shown outstanding performances. However, it is challenging to determine …

Designing robust loss functions is popular in learning with noisy labels while existing
designs did not explicitly consider the overfitting property of deep neural networks (DNNs) …

Existing multi-view representation learning methods typically follow a specific-to-uniform
pipeline, extracting latent features from each view and then fusing or aligning them to obtain …

Text segmentation is a crucial aspect of various text-related tasks, including text erasing, text
editing, and font style transfer. In recent years, multiple text segmentation datasets, such as …

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

In this work we address the escalating data labeling challenge in deep learning focusing on
the effectiveness of the Active Label Cleaning (ALC) framework in Fine-grained Visual …

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