Zobrazeno 1 - 10
of 10 381
pro vyhledávání: '"Yao, Wen"'
Publikováno v:
Applied thermal engineering(2024)
Perceiving the global field from sparse sensors has been a grand challenge in the monitoring, analysis, and design of physical systems. In this context, sensor placement optimization is a crucial issue. Most existing works require large and sufficien
Externí odkaz:
http://arxiv.org/abs/2409.18423
In the field of robotic control, designing individual controllers for each robot leads to high computational costs. Universal control policies, applicable across diverse robot morphologies, promise to mitigate this challenge. Predominantly, models ba
Externí odkaz:
http://arxiv.org/abs/2408.01230
Despite the success of input transformation-based attacks on boosting adversarial transferability, the performance is unsatisfying due to the ignorance of the discrepancy across models. In this paper, we propose a simple but effective feature augment
Externí odkaz:
http://arxiv.org/abs/2407.06714
Object detectors have demonstrated vulnerability to adversarial examples crafted by small perturbations that can deceive the object detector. Existing adversarial attacks mainly focus on white-box attacks and are merely valid at a specific viewpoint,
Externí odkaz:
http://arxiv.org/abs/2407.06688
We propose a variational modelling method with differentiable temperature for canonical ensembles. Using a deep generative model, the free energy is estimated and minimized simultaneously in a continuous temperature range. At optimal, this generative
Externí odkaz:
http://arxiv.org/abs/2404.18404
Deep neural networks (DNNs) are demonstrated to be vulnerable to universal perturbation, a single quasi-perceptible perturbation that can deceive the DNN on most images. However, the previous works are focused on using universal perturbation to perfo
Externí odkaz:
http://arxiv.org/abs/2311.01696
Convolutional neural networks (CNNs) have been demonstrated their powerful ability to extract discriminative features for hyperspectral image classification. However, general deep learning methods for CNNs ignore the influence of complex environmenta
Externí odkaz:
http://arxiv.org/abs/2310.18549
Due to the powerful ability in capturing the global information, Transformer has become an alternative architecture of CNNs for hyperspectral image classification. However, general Transformer mainly considers the global spectral information while ig
Externí odkaz:
http://arxiv.org/abs/2310.18550
Autor:
Gang Xiao, Xiao-Lei Zhang, Si-Qi Wang, Shi-Xin Lai, Ting-Ting Nie, Yao-Wen Chen, Cai-Yu Zhuang, Gen Yan, Ren-Hua Wu
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-9 (2024)
Abstract The process of chemical exchange saturation transfer (CEST) is quantified by evaluating a Z-spectra, where CEST signal quantification and Z-spectra fitting have been widely used to distinguish the contributions from multiple origins. Based o
Externí odkaz:
https://doaj.org/article/4d0c6dbd64c741338f4d90bb7264f492
Publikováno v:
Guoji Yanke Zazhi, Vol 24, Iss 8, Pp 1291-1296 (2024)
AIM: To investigate the potential causal relationship between gut microbiota(GM)and primary open-angle glaucoma(POAG)based on a two-sample Mendelian randomization(MR)analysis.METHODS: The exposure data was derived from the Genome-Wide Association Stu
Externí odkaz:
https://doaj.org/article/4cc7ccaeb1334345a87320c995b7f388