Search

Your search keyword '"Peng, Weilong"' showing total 202 results
Start Over Author "Peng, Weilong"
202 results on '"Peng, Weilong"'

1. FLAT: Flux-Aware Imperceptible Adversarial Attacks on 3D Point Clouds

Author

Tang, Keke, Huang, Lujie, Peng, Weilong, Liu, Daizong, Wang, Xiaofei, Ma, Yang, Liu, Ligang, Tian, Zhihong, Goos, Gerhard, Series 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, Leonardis, Aleš, editor, Ricci, Elisa, editor, Roth, Stefan, editor, Russakovsky, Olga, editor, Sattler, Torsten, editor, and Varol, Gül, editor

Published
2025
Full Text
View/download PDF

3. Thermal Aging State Evaluation Method for Submarine Cable Insulation Based on High-Voltage Frequency Domain Dielectric Characteristic Quantity

Author

Gao, Zhen, Peng, Weilong, Che, Haolun, Lin, Xiaobo, Ruan, Tianyu, Hao, Jian, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Jiming, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, Tan, Kay Chen, Series Editor, Yang, Qingxin, editor, Li, Zewen, editor, and Luo, An, editor

Published
2024
Full Text
View/download PDF

8. CODEs: Chamfer Out-of-Distribution Examples against Overconfidence Issue

Author

Tang, Keke, Miao, Dingruibo, Peng, Weilong, Wu, Jianpeng, Shi, Yawen, Gu, Zhaoquan, Tian, Zhihong, and Wang, Wenping

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Overconfident predictions on out-of-distribution (OOD) samples is a thorny issue for deep neural networks. The key to resolve the OOD overconfidence issue inherently is to build a subset of OOD samples and then suppress predictions on them. This paper proposes the Chamfer OOD examples (CODEs), whose distribution is close to that of in-distribution samples, and thus could be utilized to alleviate the OOD overconfidence issue effectively by suppressing predictions on them. To obtain CODEs, we first generate seed OOD examples via slicing&splicing operations on in-distribution samples from different categories, and then feed them to the Chamfer generative adversarial network for distribution transformation, without accessing to any extra data. Training with suppressing predictions on CODEs is validated to alleviate the OOD overconfidence issue largely without hurting classification accuracy, and outperform the state-of-the-art methods. Besides, we demonstrate CODEs are useful for improving OOD detection and classification., Comment: ICCV 2021

Published
2021

16. Depositional environments of complex lake systems – palaeogeographical evolution and main controls: A case study of the Lower to Middle Permian Roseneath–Epsilon–Murteree strata, Cooper Basin, Australia.

Author

Guo, Fengtao, McCabe, Peter, Feng, Zhiqiang, Zhang, Zhongmin, and Peng, Weilong

Subjects
SEQUENCE stratigraphy, GEOCHEMISTRY, LAKE sediments, LITHOFACIES, PETROLOGY, FACIES
Abstract

Lake systems are among the largest integrated depositional complexes in the continental realm. Their interplay with tectonics and climate often complicates the interpretation of depositional processes, usually resulting in a complex facies architecture that is challenging to correlate regionally. The Lower to Middle Permian Roseneath–Epsilon–Murteree strata of the Cooper Basin in Australia represent a glacially influenced fluvial–deltaic lake system, which hosts substantial petroleum resources. Despite their potential, the Roseneath–Epsilon–Murteree strata are inadequately understood in terms of regional facies architecture and their palaeogeographical implications. Using a multidisciplinary approach with robust data, including cores, petrology, wireline logs and geochemistry, the sedimentary evolution of the Roseneath–Epsilon–Murteree strata is described within a new basin‐wide sequence stratigraphic framework defined by key surfaces identified from cores and wireline logs. Detailed facies analysis of over 1400 m of cores and wireline logs from nine wells identified twelve lithofacies and eight facies associations, revealing various depositional processes and environments. The Roseneath–Epsilon–Murteree strata are interpreted as having formed in a fluvial–deltaic–lacustrine system influenced by a cold climate. First‐order and second‐order maximum flooding surfaces define a regional sequence stratigraphic framework, subdividing the Roseneath–Epsilon–Murteree strata into four sequence units (SU1, SU2, SU3 and SU4), deposited during four phases (I, II, III and IV). Cyclic stacking patterns observed in both cores and wireline logs reveal two transgressive–regressive cycles. Palaeogeographical maps of the four depositional phases suggest that the Roseneath–Epsilon–Murteree strata were dominated by a lacustrine system with some delta and mire deposits. Rivers primarily drained towards the south/south‐west from the Gidgealpa, Merrimelia, Packsaddle and Innamincka ridges ('GMI Trend') as indicated by decreasing sandstone percentages and increasing gross unit isopach maps. The deposition of the Roseneath–Epsilon–Murteree strata was primarily controlled by basin subsidence. Additionally, palaeoclimate trends and extensive glaciation in the Permian played important roles in providing sediments and affecting lake level changes. The lake system recorded by the Roseneath–Epsilon–Murteree strata serves as an analogue for other fluvial–deltaic–lacustrine systems in basins worldwide. A multidisciplinary approach, similar to the one utilized in this study, can help to elucidate their evolution and aid in resource prediction. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

19. B-spline Shape from Motion & Shading: An Automatic Free-form Surface Modeling for Face Reconstruction

Author

Peng, Weilong, Feng, Zhiyong, and Xu, Chao

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Graphics
Abstract

Recently, many methods have been proposed for face reconstruction from multiple images, most of which involve fundamental principles of Shape from Shading and Structure from motion. However, a majority of the methods just generate discrete surface model of face. In this paper, B-spline Shape from Motion and Shading (BsSfMS) is proposed to reconstruct continuous B-spline surface for multi-view face images, according to an assumption that shading and motion information in the images contain 1st- and 0th-order derivative of B-spline face respectively. Face surface is expressed as a B-spline surface that can be reconstructed by optimizing B-spline control points. Therefore, normals and 3D feature points computed from shading and motion of images respectively are used as the 1st- and 0th- order derivative information, to be jointly applied in optimizing the B-spline face. Additionally, an IMLS (iterative multi-least-square) algorithm is proposed to handle the difficult control point optimization. Furthermore, synthetic samples and LFW dataset are introduced and conducted to verify the proposed approach, and the experimental results demonstrate the effectiveness with different poses, illuminations, expressions etc., even with wild images., Comment: 9 pages, 6 figures

Published
2016

22. Contributors

Author

Arcuri, Mariano, primary, Best, James L., additional, Chen, Anqing, additional, Chen, Hongde, additional, Di Meglio, Mariano, additional, Dong, Yangkun, additional, Fan, Aiping, additional, Fu, Siyi, additional, Gao, Yi, additional, Ge, Yuzhu, additional, Guo, Yinghai, additional, Han, Xiaoqin, additional, Han, Zuozhen, additional, Hao, Bin, additional, He, Youbin, additional, He, Yuan, additional, Hou, Lianhua, additional, Huang, Xiu, additional, Jiang, Zaixing, additional, Jin, Xiaohui, additional, Jin, Zhijun, additional, Li, Hong, additional, Li, Hua, additional, Li, Jian, additional, Li, Jinbu, additional, Li, Mi, additional, Li, Xiangbo, additional, Li, Zhuangfu, additional, Liu, Chiyang, additional, Liu, Huaqing, additional, Liu, Jianliang, additional, Liu, Keyu, additional, Liu, Quanyou, additional, Liu, Shengqian, additional, Liu, Wenhui, additional, Otharán, Germán, additional, Peng, Weilong, additional, Qiao, Xiangyang, additional, Shan, Xin, additional, Su, Zhongtang, additional, Sun, Ningliang, additional, Tao, Shizhen, additional, van Loon, A.J. (Tom), additional, Wan, Xiaolong, additional, Wang, Huaichang, additional, Wang, Jing, additional, Wang, Lan, additional, Wang, Nianxi, additional, Wang, Wurong, additional, Wang, Xiaomei, additional, Wang, Xiuping, additional, Wang, Yating, additional, Wu, Shenghe, additional, Wu, Xiaoqi, additional, Xu, Shenglin, additional, Yang, Daoqing, additional, Yang, Kang, additional, Yang, Renchao, additional, Yang, Shuai, additional, Yang, Zhanlong, additional, Yin, Wei, additional, Yu, Xinghe, additional, Yue, Dali, additional, Zavala, Carlos, additional, Zhang, Can, additional, Zhang, Chenggong, additional, Zhang, Jingong, additional, Zhao, Junfeng, additional, Zhao, Junxing, additional, Zhao, Zhongjun, additional, Zhong, Jianhua, additional, Zhong, Yijiang, additional, Zorzano, Agustín, additional, and Zou, Caineng, additional

Published
2022
Full Text
View/download PDF

48. BAGEL: Backdoor Attacks against Federated Contrastive Learning

Author

Huang, Yao, Chen, Kongyang, Cao, Jiannong, Shen, Jiaxing, Wang, Shaowei, Peng, Yun, Peng, Weilong, Cai, Kechao, Huang, Yao, Chen, Kongyang, Cao, Jiannong, Shen, Jiaxing, Wang, Shaowei, Peng, Yun, Peng, Weilong, and Cai, Kechao

Abstract

Federated Contrastive Learning (FCL) is an emerging privacy-preserving paradigm in distributed learning for unlabeled data. In FCL, distributed parties collaboratively learn a global encoder with unlabeled data, and the global encoder could be widely used as a feature extractor to build models for many downstream tasks. However, FCL is also vulnerable to many security threats (e.g., backdoor attacks) due to its distributed nature, which are seldom investigated in existing solutions. In this paper, we study the backdoor attack against FCL as a pioneer research, to illustrate how backdoor attacks on distributed local clients act on downstream tasks. Specifically, in our system, malicious clients can successfully inject a backdoor into the global encoder by uploading poisoned local updates, thus downstream models built with this global encoder will also inherit the backdoor. We also investigate how to inject backdoors into multiple downstream models, in terms of two different backdoor attacks, namely the \textit{centralized attack} and the \textit{decentralized attack}. Experiment results show that both the centralized and the decentralized attacks can inject backdoors into downstream models effectively with high attack success rates. Finally, we evaluate two defense methods against our proposed backdoor attacks in FCL, which indicates that the decentralized backdoor attack is more stealthy and harder to defend.

Published
2023

Catalog

Books, media, physical & digital resources
See catalog results