About

Yuewei Lin is a Senior Computational Scientist at the Brookhaven National Laboratory, Upton, NY. He obtained his PhD degree from the University of South Carolina in Columbia, SC. Prior to that, he earned his M.S. and B.S. degrees from Chongqing University and Sichuan University in China, respectively. His research interests include AI for Science, adversarial attack and defense, domain adaptation and generalization, and computer vision techniques applied in large-scale scientific data analysis.

Research topics

• Artificial Intelligence
• Computer Science
• Machine Learning
• Computer Security
• Engineering
• Remote sensing
• Geography
• Computer vision

Selected publications

• Convolutional Neural Networks Based Remote Sensing Scene Classification under Clear and Cloudy Environments

  2021 · 51 citations

  • Computer Science
  • Artificial Intelligence
  • Computer Science

  Remote sensing (RS) scene classification has wide applications in the environmental monitoring and geological survey. In the real-world applications, the RS scene images taken by the satellite might have two scenarios: clear and cloudy environments. However, most of existing methods did not consider these two environments simultaneously. In this paper, we assume that the global and local features are discriminative in either clear or cloudy environments. Many existing Convolution Neural Networks (CNN) based models have made excellent achievements in the image classification, however they somewhat ignored the global and local features in their network structure. In this paper, we pro-pose a new CNN based network (named GLNet) with the Global Encoder and Local Encoder to extract the discriminative global and local features for the RS scene classification, where the constraints for inter-class dispersion and intra-class compactness are embedded in the GLNet training. The experimental results on two publicized RS scene classification datasets show that the proposed GLNet could achieve better performance based on many existing CNN backbones under both clear and cloudy environments.

  DOI

• Point Adversarial Self-Mining: A Simple Method for Facial Expression Recognition

  IEEE Transactions on Cybernetics · 2021 · 43 citations

  • Computer Science
  • Computer Science
  • Artificial Intelligence

  In this article, we propose a simple yet effective approach, called point adversarial self mining (PASM), to improve the recognition accuracy in facial expression recognition (FER). Unlike previous works focusing on designing specific architectures or loss functions to solve this problem, PASM boosts the network capability by simulating human learning processes: providing updated learning materials and guidance from more capable teachers. Specifically, to generate new learning materials, PASM leverages a point adversarial attack method and a trained teacher network to locate the most informative position related to the target task, generating harder learning samples to refine the network. The searched position is highly adaptive since it considers both the statistical information of each sample and the teacher network capability. Other than being provided new learning materials, the student network also receives guidance from the teacher network. After the student network finishes training, the student network changes its role and acts as a teacher, generating new learning materials and providing stronger guidance to train a better student network. The adaptive learning materials generation and teacher/student update can be conducted more than one time, improving the network capability iteratively. Extensive experimental results validate the efficacy of our method over the existing state of the arts for FER.

  DOI

• Transparent Object Tracking Benchmark

  2021 IEEE/CVF International Conference on Computer Vision (ICCV) · 2021 · 33 citations

  • Computer Science
  • Artificial Intelligence
  • Computer Science

  Visual tracking has achieved considerable progress in recent years. However, current research in the field mainly focuses on tracking of opaque objects, while little attention is paid to transparent object tracking. In this paper, we make the first attempt in exploring this problem by proposing a Transparent Object Tracking Benchmark (TOTB). Specifically, TOTB consists of 225 videos (86K frames) from 15 diverse transparent object categories. Each sequence is manually labeled with axis-aligned bounding boxes. To the best of our knowledge, TOTB is the first benchmark dedicated to transparent object tracking. In order to understand how existing trackers perform and to provide comparison for future research on TOTB, we extensively evaluate 25 state-of-the-art tracking algorithms. The evaluation results exhibit that more efforts are needed to improve transparent object tracking. Besides, we observe some nontrivial findings from the evaluation that are discrepant with some common beliefs in opaque object tracking. For example, we find that deeper features are not always good for improvements. Moreover, to encourage future research, we introduce a novel tracker, named TransATOM, which leverages transparency features for tracking and surpasses all 25 evaluated approaches by a large margin. By releasing TOTB, we expect to facilitate future research and application of transparent object tracking in both the academia and industry. The TOTB and evaluation results as well as TransATOM are available at https: //hengfan2010.github.io/projects/TOTB/.

  DOI

Frequent coauthors

• Shinjae Yoo

  Brookhaven National Laboratory

  27 shared

• Song Wang

  Guangzhou Medical University

  21 shared

• Hongkai Yu

  Cleveland State University

  15 shared

• Yuan Yan Tang

  Shandong Academy of Sciences

  12 shared

• Youjie Zhou

  Shandong University

  11 shared

• Zibo Meng

  9 shared

• Haibin Ling

  9 shared

• Bin Fang

  7 shared

Labs

• Yuewei Lin LabPI

Similar researchers at Stony Brook University

• Scott McLennanh-145
• Anatoly I. Frenkelh-101
• Vitaly Citovskyh-98
• Michael R. Douglash-91
• Minghua Zhangh-89