Search

Your search keyword '"ZHU Feng"' showing total 379 results
Start Over Author "ZHU Feng" Publisher ieee
379 results on '"ZHU Feng"'

15. UniHCP: A Unified Model for Human-Centric Perceptions

Author

Ci, Yuanzheng, primary, Wang, Yizhou, additional, Chen, Meilin, additional, Tang, Shixiang, additional, Bai, Lei, additional, Zhu, Feng, additional, Zhao, Rui, additional, Yu, Fengwei, additional, Qi, Donglian, additional, and Ouyang, Wanli, additional

Published
2023
Full Text
View/download PDF

27. Adaptive Worker Grouping for Communication-Efficient and Straggler-Tolerant Distributed SGD

Author

Zhu, Feng, Zhang, Jingjing, Simeone, Osvaldo, and Wang, Xin

Subjects
FOS: Computer and information sciences, Computer Science - Machine Learning, Information Theory (cs.IT), Computer Science - Information Theory, Machine Learning (cs.LG)
Abstract

Wall-clock convergence time and communication load are key performance metrics for the distributed implementation of stochastic gradient descent (SGD) in parameter server settings. Communication-adaptive distributed Adam (CADA) has been recently proposed as a way to reduce communication load via the adaptive selection of workers. CADA is subject to performance degradation in terms of wall-clock convergence time in the presence of stragglers. This paper proposes a novel scheme named grouping-based CADA (G-CADA) that retains the advantages of CADA in reducing the communication load, while increasing the robustness to stragglers at the cost of additional storage at the workers. G-CADA partitions the workers into groups of workers that are assigned the same data shards. Groups are scheduled adaptively at each iteration, and the server only waits for the fastest worker in each selected group. We provide analysis and experimental results to elaborate the significant gains on the wall-clock time, as well as communication load and computation load, of G-CADA over other benchmark schemes., submitted for conference publication

Published
2022

28. Feature Erasing and Diffusion Network for Occluded Person Re-Identification

Author

Wang, Zhikang, Zhu, Feng, Tang, Shixiang, Zhao, Rui, He, Lihuo, and Song, Jiangning

Subjects
FOS: Computer and information sciences, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition
Abstract

Occluded person re-identification (ReID) aims at matching occluded person images to holistic ones across different camera views. Target Pedestrians (TP) are usually disturbed by Non-Pedestrian Occlusions (NPO) and NonTarget Pedestrians (NTP). Previous methods mainly focus on increasing model's robustness against NPO while ignoring feature contamination from NTP. In this paper, we propose a novel Feature Erasing and Diffusion Network (FED) to simultaneously handle NPO and NTP. Specifically, NPO features are eliminated by our proposed Occlusion Erasing Module (OEM), aided by the NPO augmentation strategy which simulates NPO on holistic pedestrian images and generates precise occlusion masks. Subsequently, we Subsequently, we diffuse the pedestrian representations with other memorized features to synthesize NTP characteristics in the feature space which is achieved by a novel Feature Diffusion Module (FDM) through a learnable cross attention mechanism. With the guidance of the occlusion scores from OEM, the feature diffusion process is mainly conducted on visible body parts, which guarantees the quality of the synthesized NTP characteristics. By jointly optimizing OEM and FDM in our proposed FED network, we can greatly improve the model's perception ability towards TP and alleviate the influence of NPO and NTP. Furthermore, the proposed FDM only works as an auxiliary module for training and will be discarded in the inference phase, thus introducing little inference computational overhead. Experiments on occluded and holistic person ReID benchmarks demonstrate the superiority of FED over state-of-the-arts, where FED achieves 86.3% Rank-1 accuracy on Occluded-REID, surpassing others by at least 4.7%., Comment: 10 pages, 5 figures

Published
2022

37. Cross-Chamber Data Transferability Evaluation for Fault Detection and Classification in Semiconductor Manufacturing.

Author

Zhu, Feng, Jia, Xiaodong, Li, Wenzhe, Xie, Min, Li, Lishuai, and Lee, Jay

Subjects
*FEATURE extraction, *SEMICONDUCTOR manufacturing, *DISCRIMINANT analysis, *SEMICONDUCTOR industry
Abstract

Unit-to-unit variation among the production chambers is a long-lasting challenge for Fault Detection and Classification (FDC) development in the semiconductor industry. Currently, various methods are applied for knowledge transfer among chambers and generalized FDC model development. However, the existing methods cannot give a quantitative or qualitative measure for cross-chamber data transferability evaluation. This research proposes a novel methodology for data transferability evaluation and important sensor screening, which can serve as a data quality evaluation tool for any FDC model. In this research, firstly, Time Series Alignment Kernel (TSAK) is incorporated into Multidomain Discriminant Analysis (MDA) algorithm to achieve sensor-based domain generalization. Then, domain-invariant features are directly extracted for sensor visualization. After that, Fisher’s criterion ratios of the labeled good wafer samples and defective ones are computed based on the domain-invariant features of each sensor to quantitatively estimate how easy it is to transfer knowledge of each sensor among chambers, i.e., data transferability evaluation. Lastly, the proposed method develops a Recursive Feature Elimination (RFE)-based sensor selection algorithm to qualitatively analyze the importance of each sensor channel and identify the critical sensor subset. In this study, validation of the proposed method is based on two open-source datasets from real production lines. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

46. The acoustic model of bubble-liquid two-phase flow and its application in flow measurement

Author

Xiaobo Rui, Zhu Feng, Bingpu Wang, and Yu Zhang

Subjects
Oscillation, Bubble, Environmental science, Acoustic model, Two-phase flow, Mechanics, Underwater, Signal, Flow measurement, Finite element method
Abstract

The escape of underwater gas is of great significance in nature and industrial processes. The physical phenomenon of gas escape is analyzed by finite element simulation, and the pressure fluctuation and acoustic signal generated during the oscillation are studied. The experimental platform was built, and the amount of gas escaped was measured using the passive acoustic method. The results showed that the acoustic method has high accuracy. This study provides ideas for gas escaping flow measurement, and provides a reference for global climate change and industrial process state monitoring.

Published
2021

47. AutoMA: Towards Automatic Model Augmentation for Transferable Adversarial Attacks.

Author

Yuan, Haojie, Chu, Qi, Zhu, Feng, Zhao, Rui, Liu, Bin, and Yu, Nenghai

Abstract

Recent adversarial attack works attempt to improve the transferability by applying various differentiable transformations on input images. Considering the differentiable transformations and the original model together as a new model, these methods can be regarded as model augmentation that effectively derives an ensemble of models from the single original model. Despite their impressive performance, the model augmentation policies used in these methods are manually designed by experimental attempts, leaving the design of model augmentation policy an open question. In this paper, we propose an Automatic Model Augmentation (AutoMA) approach to find a strong model augmentation policy for transferable adversarial attacks. Specifically, we design a discrete search space that contains various diffierentiable transformations with different parameters and adopt reinforcement learning to search for the strong augmentation policy. The sampled augmentation policies together with the rewards they obtain during the searching process reveal several valuable observations for designing more powerful attacks using model augmentation policy: 1) Augmentation transformations on color space are less effective; 2) The transformation type diversity matters; and 3) Using small distortion for geometric transformations while larger distortion for intensity transformations. Extensive experiments show that the augmentation policy found by AutoMA achieves superior performance than existing manually designed policies in a wide range of cases. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

48. Transfer Learning Based Long Short-Term Memory Car-Following Model for Adaptive Cruise Control.

Author

Zhou, Jiazu, Wan, Jianwu, and Zhu, Feng

Abstract

Most existing studies modeled Adaptive Cruise Control (ACC) car-following (CF) behavior using conventional CF models which were originally built for human-driving vehicles (HVs) and calibrated with HV data. In this paper, firstly a learnable CF model is proposed by resorting to Long Short-Term Memory (LSTM) for ACC systems, which utilizes the ACC data for model construction and offers extraordinary adaptability and accuracy. Nevertheless, the applicability of the LSTM CF model is hindered by the scarce ACC data problem, as training the model requires a large amount of data. To address the ACC data scarcity problem, a transfer learning strategy for the LSTM model is further developed, leveraging on the large-scale open-source HV data and the similar driving patterns hidden in HV and ACC-equipped vehicles. In the transfer learning based LSTM model, a unified framework incorporating an alignment layer is developed to transfer the useful features from HV data and meanwhile calibrating the CF model with ACC data. Comparison results show that the proposed model outperforms other CF models which are built with only ACC data or using simple transfer learning methods. Further, microscopic simulations are performed to verify the applicability of the transfer learning based LSTM CF model. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

49. Effect of MODAS Data on Convergence Zone Distance Prediction

Author

Chen Qian, Zhu Feng, Zhang Yinquan, Gao Siyu, Hu Zhishun, and Zhang Shuang

Subjects
Data assimilation, Mean squared error, Computer science, Acoustics, Speed of sound, Monte Carlo method, Mesoscale meteorology, Probability density function, Random variable, Sonar
Abstract

Underwater acoustic environment (UAE) prediction is essential for accurately estimating sonar performance and making credible tactical decisions. Modular Ocean Data Assimilation System (MODAS) provides an efficient way to reconstruct real-time three-dimensional ocean sound speed field and has potential use in UAE prediction. However, the effect of MODAS on UAE prediction is not clear, which prevents MODAS from being used in practice. Taking into account that convergence zone (CZ) is a typical feature of deep-sea UAE, this paper studies the effect of MODAS on CZ distance prediction. A method is proposed to describe the accuracy of CZ distance prediction quantitatively. The method takes the CZ distance as a random variable and uses Monte Carlo sampling method to obtain the probability density function (PDF) of CZ distance. The performance of MODAS on CZ distance prediction is numerically simulated in a range-independent and a mesoscale eddy waveguides. It is shown that: (1) In the range-independent waveguide, if the sound speed disturbance of internal waves with respect to the background sound speed profile is less than the RMSE of MODAS, the prediction of CZ distance for local measured sound velocity profile is more accurate. (2) In the mesoscale eddy waveguide, the performance of MODAS is better and the performance improves as the RMSE of MODAS decreases.

Published
2021

Catalog

Books, media, physical & digital resources
See catalog results