XZXu Zhou

Xu Zhou

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Xu Zhou has a total of 48 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • IHUD-BERT: A Large-Scale Network Traffic Classification Method Based on Pre-Training Transformers and Knowledge Distillation

    by Yahui Hu, Tiancun Deng, Junping Song, Pengfei Fan, Xu Zhou

    Accurate and efficient classification of large-scale network traffic is fundamental to ensuring network Quality of Service (QoS) and security. However, existing methodologies face critical challenges. While payload-based pre-trained models have achieved success, they often rely on memorizing session-specific encryption artifacts, leading to catastrophic performance degradation under realistic “inter-flow” splitting scenarios. Furthermore, the scarcity of labeled samples and the high computational cost of large models hinder their practical deployment. To address these limitations, this paper proposes an integrated framework, IHUD-BERT, which integrates robust feature representation with knowledge distillation. We first introduce the IP Header Unit (IHU) scheme, applying a sliding window over IP packet headers. Unlike payload-based approaches, this method captures invariant behavioral patterns that remain consistent across encrypted sessions, ensuring robustness against encryption randomization while augmenting limited training data. Subsequently, a pre-trained Transformer (IHU-BERT) is constructed as a teacher model, and its comprehensive knowledge is transferred to a lightweight student model (IHUD-BERT) via hierarchical knowledge distillation. Comprehensive evaluations on multiple datasets validate our approach. The results demonstrate that while payload-based baselines collapse under strict inter-flow evaluation on encrypted traffic, our method maintains high accuracy. Notably, the lightweight IHUD-BERT achieves only a marginal performance degradation compared to its teacher counterpart while delivering millisecond-level inference latency. These results establish the proposed framework as a robust, high-precision, and efficient solution for modern encrypted traffic classification.

  • Open Access

    Efficient Cross-Datacenter Congestion Control with Fast Control Loops

    by Baosen Zhao, Jianan Sun, Xu Zhou, Wanghong Yang, Wenji Du, Fukang Chen, Yongmao Ren, Stefan Schmid

  • DRTP: A generic Differentiated Reliable Transport Protocol

    by Yongmao Ren, Yundong Zhang, Ming Yin, Anmin Xu, Xu Zhou, Cong Li, Yifang Qin, Qinghua Wu, Mohamed Ali Kaafar, Gaogang Xie


  • Open Access

    Cross-Layer Assisted Early Congestion Control for Cloud VR Services in 5G Edge Network

    by Wanghong Yang, Wenji Du, Baosen Zhao, Yongmao Ren, Jianan Sun, Xu Zhou

    Cloud virtual reality (VR) has emerged as a promising technology, offering users a highly immersive and easily accessible experience. However, the current 5G radio access network faces challenges in accommodating the bursty traffic generated by multiple cloudVR flows simultaneously, leading to congestion at the 5G base station and increased delays. In this research, we present a comprehensive quantitative analysis that highlights the underlying causes for the poor delay performance of cloudVR flows within the existing 5G protocol stack and network. To address these issues, we propose a novel cross-layer informationassisted congestion control mechanism deployed in the 5G edge network. Experiment results show that our mechanism enhances the number of concurrent flows meeting delay standards by 1.5x to 2.5x, while maintaining a smooth network load. These findings underscore the potential of leveraging 5G edge nodes as a valuable resource to effectively meet the anticipated demands of future services.

  • Retracted
    Open Access

    Feudal Multiagent Reinforcement Learning for Interdomain Collaborative Routing Optimization

    by Zhuo Li, Xu Zhou, Filip De Turck, Taixin Li, Yongmao Ren, 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.


  • Open Access

    Semantic Segmentation Network for Surface Defect Detection of Automobile Wheel Hub Fusing High-Resolution Feature and Multi-Scale Feature

    by Chaowei Tang, Xinxin Feng, Haotian Wen, Xu Zhou, Yanqing Shao, Xiaoli Zhou, Baojin Huang, 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.


  • Open Access

    Multi-Pose Face Recognition Based on Deep Learning in Unconstrained Scene

    by Shuai Ruan, Chaowei Tang, Xu Zhou, Zhuoyi Jin, Shiyu Chen, Haotian Wen, Hongbin Liu, 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.


  • Open Access

    Small-Scale Face Detection Based on Improved R-FCN

    by Chaowei Tang, Shiyu Chen, Xu Zhou, Shuai Ruan, 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.