Search

Your search keyword '"Wang Weiping"' showing total 260 results
Start Over Author "Wang Weiping" Publisher ieee
260 results on '"Wang Weiping"'

21. LSD: Adversarial Examples Detection Based on Label Sequences Discrepancy.

Author

Zhang, Shigeng, Chen, Shuxin, Hua, Chengyao, Li, Zhetao, Li, Yanchun, Liu, Xuan, Chen, Kai, Li, Zhankai, and Wang, Weiping

Abstract

Deep neural network (DNN) models have been widely used in many tasks due to their superior performance. However, DNN models are usually vulnerable to adversarial example attacks, which limits their applications in many safety-critic scenarios. How to effectively detect adversarial examples to enhance the robustness of DNN models has attracted much attention in recent years. Most adversarial example detection methods require modifying or retraining the model, which is impractical and reduces the classification accuracy of normal examples. In this paper, we propose an adversarial example detection approach that does not require modification of the DNN models and meanwhile retains the classification accuracy of normal examples. The key observation is that when we transform the input example with some operations (e.g., masking a pixel with a reference value), feed the transformed example to the target model, and use the output of the intermediate layers to predict the label of the example, the generated label sequences of adversarial examples will be extremely discrepant but the label sequences of normal examples keep nearly unchanged. Motivated by this observation, we design an approach to detect adversarial examples based on the label sequence discrepancy (LSD) of the given examples. The experimental results against five mainstream adversarial attacks on three benchmark datasets demonstrate that LSD outperforms the state-of-the-art solutions in the detection rate of adversarial examples. Moreover, LSD performs well at various confidence levels and exhibits good generalizability between different attacks. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

35. Real-time Detection and Classification for Targeted Marine Mammals

Author

Chen Yankun, Dong Chao, Yinian Liang, Wang Weiping, Zhou Defu, and Jie Li

Subjects
Noise, Data collection, Passive acoustic monitoring, Computer science, Offshore geotechnical engineering, Systems engineering
Abstract

With the continuous development of offshore engineering, major offshore projects develop rapidly. During the development of offshore engineering, different degrees of noise will be generated, and the man-made noise can have harmful effects on marine mammals. Currently, The researchers usually use Passive Acoustic Monitoring(PAM) method to monitor the marine mammals. However, it is impossible to acquire, monitor and analyze the sound of marine mammals in real time and lack of comprehensive information of marine mammals monitoring, and the data analysis and study of vocalization rules can only be carried out after data collection is completed and equipment is recovered. Therefore, this paper proposes a real-time automatic detection and classification technology to monitor targeted marine mammals efficiently and continuously timely in offshore engineering areas.

Published
2021

42. Uncertainty-Aware and Multigranularity Consistent Constrained Model for Semi-Supervised Hashing.

Author

Cheng, Shuai, Zhou, Yucan, Zhang, Wanqian, Wu, Dayan, Yang, Chule, Li, Bo, and Wang, Weiping

Subjects
SUPERVISED learning, NOISE measurement, IMAGE retrieval
Abstract

Recently, deep semi-supervised hashing methods have attracted increasing attention, which can significantly improve retrieval performance by leveraging abundant unlabeled data. These methods usually generate surrogate supervision signals to learn with unlabeled data, such as neighborhood information and augmentation invariant requirements. However, an essential issue of these methods is that the supervised signals are not always reliable, which may damage the performance. In this paper, we propose a novel Uncertainty-Aware and Multi-Granularity Consistent Constrained Semi-Supervised Hashing (UMCSH) method to alleviate the negative effects of noisy supervised signals and enlarge the inter-class distance. Specifically, our UMCSH mainly consists of an Uncertainty-Aware Instance-Level Consistency (UAILC) model and a Cluster-Based Class-Level Consistency (CBCLC) model. UAILC introduces an uncertainty estimation method to select reliable supervised signals to extract discriminative features for each unlabeled data. CBCLC establishes connections between labeled data and unlabeled data by encouraging each unlabeled sample to be close to the hash center (calculated with the labeled data) according to its pseudo-label. Extensive experimental results demonstrate the superior performance of our proposed approach compared with several state-of-the-art semi-supervised hashing methods. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results