Search

Your search keyword '"Huang, Mengyuan"' showing total 304 results
Start Over Author "Huang, Mengyuan"
304 results on '"Huang, Mengyuan"'

5. CAINNFlow: Convolutional block Attention modules and Invertible Neural Networks Flow for anomaly detection and localization tasks

Author

Yan, Ruiqing, Zhang, Fan, Huang, Mengyuan, Liu, Wu, Hu, Dongyu, Li, Jinfeng, Liu, Qiang, Jiang, Jinrong, Guo, Qianjin, and Zheng, Linghan

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence
Abstract

Detection of object anomalies is crucial in industrial processes, but unsupervised anomaly detection and localization is particularly important due to the difficulty of obtaining a large number of defective samples and the unpredictable types of anomalies in real life. Among the existing unsupervised anomaly detection and localization methods, the NF-based scheme has achieved better results. However, the two subnets (complex functions) $s_{i}(u_{i})$ and $t_{i}(u_{i})$ in NF are usually multilayer perceptrons, which need to squeeze the input visual features from 2D flattening to 1D, destroying the spatial location relationship in the feature map and losing the spatial structure information. In order to retain and effectively extract spatial structure information, we design in this study a complex function model with alternating CBAM embedded in a stacked $3\times3$ full convolution, which is able to retain and effectively extract spatial structure information in the normalized flow model. Extensive experimental results on the MVTec AD dataset show that CAINNFlow achieves advanced levels of accuracy and inference efficiency based on CNN and Transformer backbone networks as feature extractors, and CAINNFlow achieves a pixel-level AUC of $98.64\%$ for anomaly detection in MVTec AD.

Published
2022

19. Germanium on Silicon Avalanche Photodiode for High-Speed Fiber Communication

Author

Huang, Mengyuan, primary, Magruder, Kelly, additional, Malinge, Yann, additional, Fakhimi, Parastou, additional, Liao, Hao-Hsiang, additional, Kohen, David, additional, Lovell, Gregory, additional, Qian, Wei, additional, Lee, Kiyoung, additional, Brandt, Carsten, additional, Hakami, Mahtab, additional, Chen, Yen-jung, additional, Carabajal, Erin, additional, Guillermo, Erle, additional, Slavin, Seth, additional, and Liu, Ansheng, additional

Published
2023
Full Text
View/download PDF

20. DENet: Detection-driven Enhancement Network for Object Detection Under Adverse Weather Conditions

Author

Qin, Qingpao, Chang, Kan, Huang, Mengyuan, Li, Guiqing, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Wang, Lei, editor, Gall, Juergen, editor, Chin, Tat-Jun, editor, Sato, Imari, editor, and Chellappa, Rama, editor

Published
2023
Full Text
View/download PDF

23. Einstein–Stokes relation for small bubbles at the nanoscale.

Author

Zhou, Youbin, Huang, Mengyuan, Tian, Falin, Shi, Xinghua, and Zhang, Xianren

Subjects
*MOLECULAR dynamics, *BUBBLES, *BROWNIAN motion, *LIGHT scattering, *NANOPARTICLES, *COPPER, *LARGE deviations (Mathematics)
Abstract

As the physicochemical properties of ultrafine bubble systems are governed by their size, it is crucial to determine the size and distribution of such bubble systems. At present, the size or size distribution of nanometer-sized bubbles in suspension is often measured by either dynamic light scattering or the nanoparticle tracking analysis. Both techniques determine the bubble size via the Einstein–Stokes equation based on the theory of the Brownian motion. However, it is not yet clear to which extent the Einstein–Stokes equation is applicable for such ultrafine bubbles. In this work, using atomic molecular dynamics simulation, we evaluate the applicability of the Einstein–Stokes equation for gas nanobubbles with a diameter less than 10 nm, and for a comparative analysis, both vacuum nanobubbles and copper nanoparticles are also considered. The simulation results demonstrate that the diffusion coefficient for rigid nanoparticles in water is found to be highly consistent with the Einstein–Stokes equation, with slight deviation only found for nanoparticle with a radius less than 1 nm. For nanobubbles, including both methane and vacuum nanobubbles, however, large deviation from the Einstein–Stokes equation is found for the bubble radius larger than 3 nm. The deviation is attributed to the deformability of large nanobubbles that leads to a cushioning effect for collision-induced bubble diffusion. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

24. AI Online Filters to Real World Image Recognition

Author

Xiao, Hai, Shang, Jin, and Huang, Mengyuan

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence
Abstract

Deep artificial neural networks, trained with labeled data sets are widely used in numerous vision and robotics applications today. In terms of AI, these are called reflex models, referring to the fact that they do not self-evolve or actively adapt to environmental changes. As demand for intelligent robot control expands to many high level tasks, reinforcement learning and state based models play an increasingly important role. Herein, in computer vision and robotics domain, we study a novel approach to add reinforcement controls onto the image recognition reflex models to attain better overall performance, specifically to a wider environment range beyond what is expected of the task reflex models. Follow a common infrastructure with environment sensing and AI based modeling of self-adaptive agents, we implement multiple types of AI control agents. To the end, we provide comparative results of these agents with baseline, and an insightful analysis of their benefit to improve overall image recognition performance in real world.

Published
2020

Catalog

Books, media, physical & digital resources
See catalog results