Xu Zhou

Prof. Xu Zhou

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 July 2020 in Applied Sciences
Verified
Journal Article
Open access
PDF file
SRShuai Ruan
Shuai Ruan
CTChaowei Tang
Chaowei Tang
XZXu Zhou
Xu Zhou
ZJZhuoyi Jin
Zhuoyi Jin
SCShiyu Chen
Shiyu Chen
DTDong Tang
Dong Tang
At present, deep learning drives the rapid development of face recognition. However, in the unconstrained scenario, the change of facial posture has a great impact on face recognition. Moreover, the current model still has some shortcomings in accuracy and robustness. The existing research has formulated two methods to solve the above problems. One method is to model and train each pose separately. Then, a fusion decision will be made. The other method is to make “frontal” faces on the image or feature level and transform them into “frontal” face recognition. Based on the second idea, we propose a profile to the frontal revise mapping (PTFRM) module. This module realizes the revision of arbitrary poses on the feature level and transforms the multi-pose features into an approximate frontal representation to enhance the recognition ability of the existing recognition models. Finally, we evaluate the PTFRM on unconstrained face validation benchmark datasets such as Labeled Faces in the Wild (LFW), Celebrities in Frontal Profile (CFP), and IARPA Janus Benchmark A(IJB-A). Results show that the chosen method for this study achieves good performance.

18 June 2020 in Applied Sciences
Verified
Journal Article
Open access
PDF file
CTChaowei Tang
Chaowei Tang
SCShiyu Chen
Shiyu Chen
XZXu Zhou
Xu Zhou
SRShuai Ruan
Shuai Ruan
HWHaotian Wen
Haotian Wen
Face detection is an important basic technique for face-related applications, such as face analysis, recognition, and reconstruction. Images in unconstrained scenes may contain many small-scale faces. The features that the detector can extract from small-scale faces are limited, which will cause missed detection and greatly reduce the precision of face detection. Therefore, this study proposes a novel method to detect small-scale faces based on region-based fully convolutional network (R-FCN). First, we propose a novel R-FCN framework with the ability of feature fusion and receptive field adaptation. Second, a bottom-up feature fusion branch is established to enrich the local information of high-layer features. Third, a receptive field adaptation block (RFAB) is proposed to ensure that the receptive field can be adaptively selected to strengthen the expression ability of features. Finally, we improve the anchor setting method and adopt soft non-maximum suppression (SoftNMS) as the selection method of candidate boxes. Experimental results show that average precision for small-scale face detection of R-FCN with feature fusion branch and RFAB (RFAB-f-R-FCN) is improved by 0.8%, 2.9%, and 11% on three subsets of Wider Face compared with that of R-FCN.

9 November 2021 in Applied Sciences
Verified
Journal Article
Open access
PDF file
CTChaowei Tang
Chaowei Tang
XFXinxin Feng
Xinxin Feng
HWHaotian Wen
Haotian Wen
XZXu Zhou
Xu Zhou
YSYanqing Shao
Yanqing Shao
YLYunzhen Li
Yunzhen Li
Surface defect detection of an automobile wheel hub is important to the automobile industry because these defects directly affect the safety and appearance of automobiles. At present, surface defect detection networks based on convolutional neural network use many pooling layers when extracting features, reducing the spatial resolution of features and preventing the accurate detection of the boundary of defects. On the basis of DeepLab v3+, we propose a semantic segmentation network for the surface defect detection of an automobile wheel hub. To solve the gridding effect of atrous convolution, the high-resolution network (HRNet) is used as the backbone network to extract high-resolution features, and the multi-scale features extracted by the Atrous Spatial Pyramid Pooling (ASPP) of DeepLab v3+ are superimposed. On the basis of the optical flow, we decouple the body and edge features of the defects to accurately detect the boundary of defects. Furthermore, in the upsampling process, a decoder can accurately obtain detection results by fusing the body, edge, and multi-scale features. We use supervised training to optimize these features. Experimental results on four defect datasets (i.e., wheels, magnetic tiles, fabrics, and welds) show that the proposed network has better F1 score, average precision, and intersection over union than SegNet, Unet, and DeepLab v3+, proving that the proposed network is effective for different defect detection scenarios.

27 June 2022 in Peer-to-Peer Networking and Applications
Verified
Journal Article
Closed access
PDF file
TLTaixin Li
Taixin Li
XZXu Zhou
Xu Zhou
SYShen Yan
Shen Yan
XZXiaobo Zhang
Xiaobo Zhang

8 August 2024 in Computer Communications
Verified
Journal Article
Closed access
YRYongmao Ren
Yongmao Ren
YZYundong Zhang
Yundong Zhang
MYMing Yin
Ming Yin
AXAnmin Xu
Anmin Xu
XZXu Zhou
Xu Zhou
GXGaogang Xie
Gaogang Xie

27 March 2022 in Wireless Communications and Mobile Computing
Verified
Journal Article
Open access
PDF file
ZLZhuo Li
Zhuo Li
XZXu Zhou
Xu Zhou
FTFilip De Turck
Filip De Turck
TLTaixin Li
Taixin Li
YRYongmao Ren
Yongmao Ren
YQYifang Qin
Yifang Qin
In view of the inability of traditional interdomain routing schemes to meet the sudden network changes and adapt the routing policy accordingly, many optimization schemes such as modifying Border Gateway Protocol (BGP) parameters and using software-defined network (SDN) to optimize interdomain routing decisions have been proposed. However, with the change and increase of the demand for network data transmission, the high latency and flexibility of these mechanisms have become increasingly prominent. Recent researches have addressed these challenges through multiagent reinforcement learning (MARL), which can be capable of dynamically meeting interdomain requirements, and the multiagent Markov Decision Process (MDP) is introduced to construct this routing optimization problem. Thus, in this paper, an interdomain collaborative routing scheme is proposed in interdomain collaborative architecture. The proposed Feudal Multiagent Actor-Critic (FMAAC) algorithm is designed based on multiagent actor-critic and feudal reinforcement learning to solve this competition-cooperative problem. Our multiagent learns about the optimal interdomain routing decisions, focused on different optimization objectives such as end-to-end delay, throughput, and average delivery rate. Experiments were carried out in the interdomain testbed to verify the convergence and effectiveness of the FMAAC algorithm. Experimental results show that our approach can significantly improve various Quality of Service (QoS) indicators, containing reduced end-to-end delay, increased throughput, and guaranteed over 90% average delivery rate.