Benlin Liu

I am a Ph.D. student in Paul G. Allen School of Computer Science & Engineering, University of Washington, working with Steven M. Seitz, Brian Curless, and Ira Kemelmacher-Shlizerman. I am affiliated with UW Graphics and Imaging Laboratory (GRAIL) and UW Reality Lab.

I receive my master degree from Department of Computer Science, UCLA, where I was a research assistant under the supervision of Prof. Cho-jui Hsieh . I also collaborated with Prof. Xiaolong Wang at UCSD . I obtained my BEng. degree from the Department of Electronic Engineering , Tsinghua University , and I worked with Prof. Jiwen Lu of the Department of Automation . During undergraduate, I visited the GRASP Lab at University of Pennsylvania and worked with Prof. Jianbo Shi.

I am broadly interested in computer vision and machine learning. My current research focuses on 3D vision and efficient deep learning methods.

Email  /  CV  /  Google Scholar  /  Github Twitter

profile photo

  • 2020-12: DynamicViT is accepted to NeurIPS 2021.
  • 2020-12: Two papers are accepted to ICCV 2021.
  • 2020-12: One paper on image classification is accepted to AAAI 2021.
  • 2020-07: One paper on knowledge distillation is accepted by ECCV 2020.
  • Publications

    * indicates equal contribution

    dise DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification
    Yongming Rao, Wenliang Zhao, Benlin Liu, Jiwen Lu, Jie Zhou, Cho-Jui Hsieh
    Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS), 2021
    [Paper][Project Page][Code][Video]

    We propose a dynamic token sparsification framework to prune redundant tokens progressively and dynamically for vision transformer acceleration.

    dise RandomRooms: Unsupervised Pre-training from Synthetic Shapes and Randomized Layouts for 3D Object Detection
    Yongming Rao*, Benlin Liu*, Yi Wei, Jiwen Lu, Cho-Jui Hsieh, Jie Zhou
    IEEE/CVF International Conference on Computer Vision (ICCV), 2021

    We propose to generate random layouts of a scene by making use of the objects in the synthetic CAD dataset and learn the 3D scene representation by applying object-level contrastive learning on two random scenes generated from the same set of synthetic objects.

    dise Robust Object Detection via Instance-Level Temporal Cycle Confusion
    Xin Wang, Thomas E. Huang*, Benlin Liu*, Fisher Yu, Xiaolong Wang, Joseph E. Gonzalez, Trevor Darrell
    IEEE/CVF International Conference on Computer Vision (ICCV), 2021
    [Paper][Project Page]

    We introduce a new self-supervised task on videos to improve the out-of-domain generalization of object detectors.

    dise Multi-ProxyWasserstein Classifier for Image Classification
    Benlin Liu*, Yongming Rao*, Jiwen Lu, Jie Zhou, Cho-Jui Hsieh
    35th AAAI Conference on Artificial Intelligence (AAAI), 2021

    We present a new Multi-Proxy Wasserstein Classifier to imporve the image classification models by calculating a non-uniform matching flow between the elements in the feature map of a sample and multiple proxies of a class using optimal transport theory.

    dise MetaDistiller: Network Self-Boosting via Meta-Learned Top-Down Distillation
    Benlin Liu, Yongming Rao, Jiwen Lu, Jie Zhou, Cho-Jui Hsieh
    16th European Conference on Computer Vision (ECCV), 2020

    We boost the performance of CNNs by learning soft targets for shallow layers via meta-learning.

    Honors and Awards

  • 1st place in Momenta Lane Detection Challenge
  • Academic Services

  • Conference Reviewer: ICLR 2022, CVPR 2021, WACV 2021-2022

  • Website Template

    © Benlin Liu | Last updated: Nov 29, 2020