Shen Zhang

Siyuan Wei, Tianzhu Ye, Shen Zhang et al.

Although vision transformers (ViTs) have shown promising results in various computer vision tasks recently, their high computational cost limits their practical applications. Previous approaches that prune redundant tokens have demonstrated a good trade-off between performance and computation costs. Nevertheless, errors caused by pruning strategies can lead to significant information loss. Our quantitative experiments reveal that the impact of pruned tokens on performance should be noticeable. To address this issue, we propose a novel joint Token Pruning & Squeezing module (TPS) for compressing vision transformers with higher efficiency. Firstly, TPS adopts pruning to get the reserved and pruned subsets. Secondly, TPS squeezes the information of pruned tokens into partial reserved tokens via the unidirectional nearest-neighbor matching and similarity-based fusing steps. Compared to state-of-the-art methods, our approach outperforms them under all token pruning intensities. Especially while shrinking DeiT-tiny&small computational budgets to 35%, it improves the accuracy by 1%-6% compared with baselines on ImageNet classification. The proposed method can accelerate the throughput of DeiT-small beyond DeiT-tiny, while its accuracy surpasses DeiT-tiny by 4.78%. Experiments on various transformers demonstrate the effectiveness of our method, while analysis experiments prove our higher robustness to the errors of the token pruning policy. Code is available at https://github.com/megvii-research/TPS-CVPR2023.

Shen Zhang, Shibo Zhang, Bingnan Wang et al.

In this survey paper, we systematically summarize existing literature on bearing fault diagnostics with machine learning (ML) and data mining techniques. While conventional ML methods, including artificial neural network (ANN), principal component analysis (PCA), support vector machines (SVM), etc., have been successfully applied to the detection and categorization of bearing faults for decades, recent developments in deep learning (DL) algorithms in the last five years have sparked renewed interest in both industry and academia for intelligent machine health monitoring. In this paper, we first provide a brief review of conventional ML methods, before taking a deep dive into the state-of-the-art DL algorithms for bearing fault applications. Specifically, the superiority of DL based methods over conventional ML methods are analyzed in terms of fault feature extraction and classification performances; many new functionalities enabled by DL techniques are also summarized. In addition, to obtain a more intuitive insight, a comparative study is conducted on the classification accuracy of different algorithms utilizing the open-source Case Western Reserve University (CWRU) bearing dataset. Finally, to facilitate the transition on applying various DL algorithms to bearing fault diagnostics, detailed recommendations and suggestions are provided for specific application conditions such as the setup environment, the data size, and the number of sensors and sensor types. Future research directions to further enhance the performance of DL algorithms on health monitoring are also discussed.

Shen Zhang, Haojie Zhang, Jing Zhang et al.

In human-computer interaction, it is crucial for agents to respond to human by understanding their emotions. Unraveling the causes of emotions is more challenging. A new task named Multimodal Emotion-Cause Pair Extraction in Conversations is responsible for recognizing emotion and identifying causal expressions. In this study, we propose a multi-stage framework to generate emotion and extract the emotion causal pairs given the target emotion. In the first stage, Llama-2-based InstructERC is utilized to extract the emotion category of each utterance in a conversation. After emotion recognition, a two-stream attention model is employed to extract the emotion causal pairs given the target emotion for subtask 2 while MuTEC is employed to extract causal span for subtask 1. Our approach achieved first place for both of the two subtasks in the competition.

Shuchao Pang, Zhenghan Chen, Shen Zhang et al.

Deep neural networks for 3D point clouds have been demonstrated to be vulnerable to adversarial examples. Previous 3D adversarial attack methods often exploit certain information about the target models, such as model parameters or outputs, to generate adversarial point clouds. However, in realistic scenarios, it is challenging to obtain any information about the target models under conditions of absolute security. Therefore, we focus on transfer-based attacks, where generating adversarial point clouds does not require any information about the target models. Based on our observation that the critical features used for point cloud classification are consistent across different DNN architectures, we propose CFG, a novel transfer-based black-box attack method that improves the transferability of adversarial point clouds via the proposed Critical Feature Guidance. Specifically, our method regularizes the search of adversarial point clouds by computing the importance of the extracted features, prioritizing the corruption of critical features that are likely to be adopted by diverse architectures. Further, we explicitly constrain the maximum deviation extent of the generated adversarial point clouds in the loss function to ensure their imperceptibility. Extensive experiments conducted on the ModelNet40 and ScanObjectNN benchmark datasets demonstrate that the proposed CFG outperforms the state-of-the-art attack methods by a large margin.

Shibo Zhang, Yaxuan Li, Shen Zhang et al.

Mobile and wearable devices have enabled numerous applications, including activity tracking, wellness monitoring, and human--computer interaction, that measure and improve our daily lives. Many of these applications are made possible by leveraging the rich collection of low-power sensors found in many mobile and wearable devices to perform human activity recognition (HAR). Recently, deep learning has greatly pushed the boundaries of HAR on mobile and wearable devices. This paper systematically categorizes and summarizes existing work that introduces deep learning methods for wearables-based HAR and provides a comprehensive analysis of the current advancements, developing trends, and major challenges. We also present cutting-edge frontiers and future directions for deep learning-based HAR.

Shen Zhang, Oliver Wallscheid, Mario Porrmann

This review paper systematically summarizes the existing literature on utilizing machine learning (ML) techniques for the control and monitoring of electric machine drives. It is anticipated that with the rapid progress in learning algorithms and specialized embedded hardware platforms, machine learning-based data-driven approaches will become standard tools for the automated high-performance control and monitoring of electric drives. Additionally, this paper also provides some outlook toward promoting its widespread application in the industry with a focus on deploying ML algorithms onto embedded system-on-chip (SoC) field-programmable gate array (FPGA) devices.

Fei Ye, Shen Zhang, Pin Wang et al.

In this survey, we systematically summarize the current literature on studies that apply reinforcement learning (RL) to the motion planning and control of autonomous vehicles. Many existing contributions can be attributed to the pipeline approach, which consists of many hand-crafted modules, each with a functionality selected for the ease of human interpretation. However, this approach does not automatically guarantee maximal performance due to the lack of a system-level optimization. Therefore, this paper also presents a growing trend of work that falls into the end-to-end approach, which typically offers better performance and smaller system scales. However, their performance also suffers from the lack of expert data and generalization issues. Finally, the remaining challenges applying deep RL algorithms on autonomous driving are summarized, and future research directions are also presented to tackle these challenges.

Shuang Guo, Bo Liu, Shen Zhang et al.

In this paper, we extend a famous motion planning approach GPMP2 to multi-robot cases, yielding a novel centralized trajectory generation method for the multi-robot formation. A sparse Gaussian Process model is employed to represent the continuous-time trajectories of all robots as a limited number of states, which improves computational efficiency due to the sparsity. We add constraints to guarantee collision avoidance between individuals as well as formation maintenance, then all constraints and kinematics are formulated on a factor graph. By introducing a global planner, our proposed method can generate trajectories efficiently for a team of robots which have to get through a width-varying area by adaptive formation change. Finally, we provide the implementation of an incremental replanning algorithm to demonstrate the online operation potential of our proposed framework. The experiments in simulation and real world illustrate the feasibility, efficiency and scalability of our approach.

Shen Zhang, Fei Ye, Bingnan Wang et al.

Most of the data-driven approaches applied to bearing fault diagnosis up to date are established in the supervised learning paradigm, which usually requires a large set of labeled data collected a priori. In practical applications, however, obtaining accurate labels based on real-time bearing conditions can be far more challenging than simply collecting a huge amount of unlabeled data using various sensors. In this paper, we thus propose a semi-supervised learning approach for bearing anomaly detection using variational autoencoder (VAE) based deep generative models, which allows for effective utilization of dataset when only a small subset of data have labels. Finally, a series of experiments is performed using both the Case Western Reserve University (CWRU) bearing dataset and the University of Cincinnati's Center for Intelligent Maintenance Systems (IMS) dataset. The experimental results demonstrate that the proposed semi-supervised learning scheme greatly outperforms two mainstream semi-supervised learning approaches and a baseline supervised convolutional neural network approach, with the overall accuracy improvement ranging between 3% to 30% using different proportions of labeled samples.

Shen Zhang, Shibo Zhang, Sufei Li et al.

The optimization of electric machines at multiple operating points is crucial for applications that require frequent changes on speeds and loads, such as the electric vehicles, to strive for the machine optimal performance across the entire driving cycle. However, the number of objectives that would need to be optimized would significantly increase with the number of operating points considered in the optimization, thus posting a potential problem in regards to the visualization techniques currently in use, such as in the scatter plots of Pareto fronts, the parallel coordinates, and in the principal component analysis (PCA), inhibiting their ability to provide machine designers with intuitive and informative visualizations of all of the design candidates and their ability to pick a few for further fine-tuning with performance verification. Therefore, this paper proposes the utilization of t-distributed stochastic neighbor embedding (t-SNE) to visualize all of the optimization objectives of various electric machines design candidates with various operating conditions, which constitute a high-dimensional set of data that would lie on several different, but related, low-dimensional manifolds. Finally, two case studies of switched reluctance machines (SRM) are presented to illustrate the superiority of then t-SNE when compared to traditional visualization techniques used in electric machine optimizations.