Lei Huang (黄 雷)

Ph.D. Candidate

State Key Laboratory of Software Development Environment
School of Computer Science and Engineering, Beihang University, China

Email: huanglei AT nlsde DOT buaa DOT edu DOT cn
Address: Room G602, New Main Building, 37 Xueyuan Road, Haidian, Beijing, China 100191

[Research Interests] | [Publication] | [Professional Activities] |[Education] | [Awards and Honors] | [Source Code]| [Miscellaneous] | [CV]

  • Note: I graduated and moved to the Inception Institute of Artificial Intelligence (IIAI) as a research scientist. I have moved my personal homepage to [here], and this homepage will not be updated in time.
  • NEW March 2019: Two papers are accpeted by CVPR 2019.
  • NEW September 2018: Mete Ozay and I organize a tutorial named "Normalization Methods for Training Deep Neural Networks: Theory and Practice" at ECCV 2018. The slides can be found here .
  • NEW Feb 2018: Our paper is accepted by CVPR 2018("Decorrelated Batch Normalization"). The paper can be available on [arxiv] and the code can be available on [GitHub]
  • NEW November 2017: Our paper is accepted by AAAI 2018("Orthogonal Weight Normalization: Solution to Optimization over Multiple Dependent Stiefel Manifolds in Deep Neural Networks")
  • NEW Our paper "Projection Based Weight Normalization for Deep Neural Networks" can be available on [arxiv] and the code can be available on [GitHub]
  • NEW  Sep 2017: I will atend the Doctoral Symposium at ICIP 2017, on 19 September at China National Convention Center (CNCC), BeiJing. I will present my research about 'Normalization Techniques in Training Deep Neural Networks'
  • NEW  Jul 2017: One paper accepted by IEEE ICCV 2017.

  • Research Interests

    • Machine Learning and Computer Vision: Optimization and Normalization Techniques on Deep Learning, Semi-Supervised Learning, Active Learning, Manifold Learning, Adversarial Examples, Kernel Methods, Image Translation, Human Pose Estimation
    • Multimedia Content Analysis and Image Retrieval: Large Scale Annotation, Hash Based Nearest Neighbor Search

    Publications

    Iterative Normalization: Beyond Standardization towards Efficient Whitening
    Lei Huang, Yi Zhou, Fan Zhu, Li Liu, Ling Shao
    CVPR 2019 (accept)
    Collaborative Learning of Semi-Supervised Segmentation and Classification for Medical Images
    Yi Zhou, Xiaodong He, Lei Huang, Li Liu, Fan Zhu, Shanshan cui, Ling Shao
    CVPR 2019 (accept)
    Decorrelated Batch Normalization
    Lei Huang, Dawei Yang, Bo Lang, Jia Deng
    CVPR 2018
    Orthogonal Weight Normalization: Solution to Optimization over Multiple Dependent Stiefel Manifolds in Deep Neural Networks
    Lei Huang, Xianglong Liu, Bo Lang, Admas Wei Yu, Bo Li
    AAAI 2018 (Oral), (arXiv:1709.06079)
    Projection Based Weight Normalization for Deep Neural Networks
    Lei Huang, Xianglong Liu, Bo Lang, Bo Li
    preprint (arXiv:1710.02338)
    Block-normalized Gradient Method: an Empirical Study for Training Deep Nerual Network
    Adams Wei Yu, Lei Huang, Qihang Lin, Ruslan Salakhutdinov, Jaime Carbonell.
    preprint (arXiv:1707.04822)
    Centered Weight Normalization in Accelerating Training of Deep Neural Networks
    Lei Huang, Xianglong Liu, Yang Liu, Bo Lang, Dacheng Tao
    IEEE ICCV, 2017
    DGCNN: Disordered Graph Convolutional Neural Network Based on the Gaussian Mixture Model
    Bo Wu, Yang Liu, Bo Lang, Lei Huang
    preprint (arXiv:1712.03563)
    Learning Joint Multimodal Representation Based on Multi-fusion Deep Neural Networks
    Zepeng Gu, Bo Lang, Tongyu Yue, Lei Huang
    The 24th International Conference on Neural Information Processing (ICONIP 2017), (Oral)
    Query-adaptive hash code ranking for large-scale multi-view visual search
    Xianglong Liu, Lei Huang, Cheng Deng, Bo Lang, Dacheng Tao
    IEEE Transactions on Image Processing (TIP). 2016
    A Novel Rotation Adaptive Object Detection Method Based on Pair Hough Model
    Yang Liu, Lei Huang, Xianglong Liu, Bo Lang
    Neurocomputing, 2016
    Efficient Segmentation for Region-based Image Retrieval Using Edge Integrated Minimum Spanning Tree
    Yang Liu, Lei Huang, Siqi Wang, Xianglong Liu, Bo Lang
    ICPR. 2016
    Multi-View Complementary Hash Tables for Nearest Neighbor Search
    Xianglong Liu, Lei Huang, Cheng Deng, Jiwen Lu, Bo Lang
    IEEE ICCV, 2015
    Graph-based Active Semi-supervised Learning: a New Perspective for Relieving Multi-class Annotation Labor
    Lei Huang, Yang Liu, Xianglong Liu, Xindong Wang, Bo Lang
    IEEE ICME, 2014
    Online Semi-Supervised Annotation via Proxy-based Local Consistency Propagation
    Lei Huang, Xianglong Liu, Binqiang Ma, Bo Lang
    Neurocomputing, 2014
    Query-Adaptive Hash Code Ranking for Fast Nearest Neighbor Search
    Tianxu Ji, Xianglong Liu, Cheng Deng, Lei Huang, Bo Lang
    ACM MM (short paper), 2014
    Efficient Semi-supervised Annotation with Proxy-based Local Consistency Propagation
    Lei Huang, Yang Wang, Xianglong Liu, Bo Lang
    IEEE ICME, 2013
    AUDR: An Advanced Unstructured Data Repository
    Xianglong Liu, Bo Lang, Wei Yu, Junwu Luo, Lei Huang
    The 6th International Conference on Pervasive Computing and Applications (ICPCA6) South Africa, 2011

    Talk Slides


    Professional Activities

    Education

    • Sep. 2015 - Oct. 2016
      • Visiting Ph.D student in Vision & Learning Lab, at the University of Michigan, Ann Arbor
      • Research advisor: Profs. Jia Deng
    • Sep. 2011 - Present
      • Ph.D student in Computer Science, School of Computer Science and Engineering, Beihang University
      • advisor: Profs. Wei Li and co-advised by Profs. Bo Lang
    • Sep. 2010 - Sep. 2011
      • Master student in Computer Science, School of Computer Science and Engineering, Beihang University
      • advisor: Profs. Wei Li and co-advised by Profs. Bo Lang
    • Sep. 2006 - Jun. 2010
      • B.Sc in Computer Science, School of Computer Science and Engineering, Beihang University

    Awards and Honors

    • China Scholarship Council (CSC) Scholarship, 2015.

    • The National Scholarship for Ph.D. candidate, 2014.

    • The Guanghua Scholarship, 2013.

    • Outstanding graduate, Beihang University. 2010

    • The Second Class Prize of the 2nd Beihang University Dancing Contest, 2010

    • The Second Class Prize of the 1st Beihang University Dancing Contest, 2008.

    • The Third Class Scholarship for Academic Performance in Beihang University, 2009

    • The Third Class Scholarship for Contest Excellence in Beihang University, 2008

    • The Third Class Prize of the 18th Mathematics Contest for College Students in Beijing, 2007.

    • The Third Class Prize of the 24th National Physics Contest for College Students, 2007.

    • The Second Class Scholarship for Excellent Freshman in Beihang University, 2006.


    Source Code

    • DBN: This project is the Torch implementation of the paper : Decorrelated Batch normalization (arXiv:1804.08450).

    • OWN: This project is the Torch implementation of the paper : orthogonal weight normalization method for solving orthogonality constraints over Steifel manifold in deep neural networks (arXiv:1709.06079).

    • CWN: This project is the Torch implementation of our accepted ICCV 2017 paper: Centered Weight Normalization in Accelerating Training of Deep Neural Networks

    • NormProjection: This project is the Torch implementation of the paper: Projection Based Weight Normalization for Deep Neural Networks (arXiv:1710.02338)

    • Ladder_deepSSL_NP: The reimplementation of Ladder networks with projection based weight normalization. We achieved test errors as 2.52%, 1.06%, and 0.91% on Permunate invariant MNIST dataset with 20, 50, and 100 labeled samples respectively, which is the state-of-the-art results.


    Miscellaneous