F Dunkin, X Li, C Hu, G Wu, H Li, X Lu… - Advanced Engineering …, 2024 - Elsevier
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 …
H Song, M Kim, JG Lee - Proceedings of the AAAI Conference on …, 2024 - ojs.aaai.org
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) …
R Wang, H Sun, Y Ma, X Xi… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
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 …
H Yu, X Wang, K Niu, B Li, X Xue - Proceedings of the 31st ACM …, 2023 - dl.acm.org
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 …
A Pal - Proceedings of the IEEE/CVF Conference on …, 2024 - openaccess.thecvf.com
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 …
M Wang, R Hu, X Zhu, D Zhu, X Wang - Knowledge-Based Systems, 2024 - Elsevier
Fatigue is a significant safety concern across various domains, and accurate detection is vital. However, the commonly employed fine-grained labels (seconds-based) frequently …