[HTML][HTML] Beyond explaining: Opportunities and challenges of XAI-based model improvement

L Weber, S Lapuschkin, A Binder, W Samek - Information Fusion, 2023 - Elsevier
Abstract Explainable Artificial Intelligence (XAI) is an emerging research field bringing
transparency to highly complex and opaque machine learning (ML) models. Despite the …

Progress in prediction of remaining useful life of hydrogen fuel cells based on deep learning

W He, T Liu, W Ming, Z Li, J Du, X Li, X Guo… - … and Sustainable Energy …, 2024 - Elsevier
Hydrogen fuel cells are promising power sources that directly transform the chemical energy
produced by the chemical reaction of hydrogen and oxygen into electrical energy. However …

Global attention mechanism: Retain information to enhance channel-spatial interactions

Y Liu, Z Shao, N Hoffmann - arXiv preprint arXiv:2112.05561, 2021 - arxiv.org
A variety of attention mechanisms have been studied to improve the performance of various
computer vision tasks. However, the prior methods overlooked the significance of retaining …

Fcanet: Frequency channel attention networks

Z Qin, P Zhang, F Wu, X Li - Proceedings of the IEEE/CVF …, 2021 - openaccess.thecvf.com
Attention mechanism, especially channel attention, has gained great success in the
computer vision field. Many works focus on how to design efficient channel attention …

Rotate to attend: Convolutional triplet attention module

D Misra, T Nalamada… - Proceedings of the …, 2021 - openaccess.thecvf.com
Benefiting from the capability of building inter-dependencies among channels or spatial
locations, attention mechanisms have been extensively studied and broadly used in a …

EPSANet: An efficient pyramid squeeze attention block on convolutional neural network

H Zhang, K Zu, J Lu, Y Zou… - Proceedings of the asian …, 2022 - openaccess.thecvf.com
Recently, it has been demonstrated that the performance of a deep convolutional neural
network can be effectively improved by embedding an attention module into it. In this work, a …

Dual-sampling attention network for diagnosis of COVID-19 from community acquired pneumonia

X Ouyang, J Huo, L Xia, F Shan, J Liu… - … on Medical Imaging, 2020 - ieeexplore.ieee.org
The coronavirus disease (COVID-19) is rapidly spreading all over the world, and has
infected more than 1,436,000 people in more than 200 countries and territories as of April 9 …

Feature refinement and filter network for person re-identification

X Ning, K Gong, W Li, L Zhang, X Bai… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
In the task of person re-identification, the attention mechanism and fine-grained information
have been proved to be effective. However, it has been observed that models often focus on …

Attention, please! A survey of neural attention models in deep learning

A de Santana Correia, EL Colombini - Artificial Intelligence Review, 2022 - Springer
In humans, Attention is a core property of all perceptual and cognitive operations. Given our
limited ability to process competing sources, attention mechanisms select, modulate, and …

Facial action unit detection with transformers

GM Jacob, B Stenger - … of the IEEE/CVF conference on …, 2021 - openaccess.thecvf.com
Abstract The Facial Action Coding System is a taxonomy for fine-grained facial expression
analysis. This paper proposes a method for detecting Facial Action Units (FAU), which …