Ziwei Wang

Ziwei Wang is a PhD candidate at the Intelligent Vision Group (IVG), Department of Automation, Tsinghua University, advised by Prof. Jiwen Lu. He received the BS degree from the Department of Physics, Tsinghua University, China, in 2018. His research interests include tiny machine learning, robotic vision and scene understanding. He has published over 10 scientific papers in the IEEE Transactions on Pattern Analysis and Machine Intelligence, CVPR, ICCV, ECCV and IROS. He serves as a regular reviewer member for the IEEE Transactions on Image Processing, IEEE Transactions on Circuits and Systems for Video Technology, Pattern Recognition Letters, CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, WACV, ACCV, ICPR, ICME and ICIP.

Email  /  CV  /  Google Scholar  /  Github

profile photo
News

  • 2022-07: One paper on model explanation is accepted to ECCV 2022.
  • 2022-06: One paper on robotic grasping and one paper on robotic exploration are accepted to IROS 2022.
  • 2022-03: One paper on binary representation learning is accepted to TPAMI.
  • 2022-03: One paper on network architecture search is accepted to CVPR 2022.
  • 2021-07: One paper on mixed-precision quantization and one paper on unsupervised learning are accepted to ICCV 2021.
  • 2021-01: One paper on efficient detection is accepted to TPAMI.
  • 2020-07: One paper on active hashing is accepted to ECCV 2020.
  • 2020-04: One paper on network quantization is accepted to TPAMI.
  • 2020-02: One paper on efficient detection is accepted to CVPR 2020.
  • 2019-02: One paper on network quantization is accepted to CVPR 2019.
  • Publications
    dise Shap-CAM: Visual Explanations for Convolutional Neural Networks based on Shapley Value
    Quan Zheng, Ziwei Wang, Jie Zhou, Jiwen Lu
    17th European Conference on Computer Vision (ECCV), 2022
    [PDF]

    we develop a post-hoc visual explanation method based on the Shapley value in class activation mapping.

    dise Smart Explorer: Recognizing Objects in Dense Clutter via Interactive Exploration
    Zhenyu Wu*, Ziwei Wang*, Zibu Wei, Yi Wei, Haibin Yan
    IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022.
    [PDF] [Demo] [Code]

    We propose an interactive exploration framework called Smart Explorer for recognizing all objects in dense clutters.

    dise GE-Grasp: Efficeint Target Oriented Grasping in Dense Clutter
    Zhan Liu, Ziwei Wang, Sichao Huang, Jie Zhou, Jiwen Lu
    IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022.
    [PDF] [Demo] [Code]

    we present a generic framework for robotic motion planning in dense clutter with diverse action primitives and generator-evaluator architectures.

    dise Learning Deep Binary Descriptors via Bitwise Interaction Mining
    Ziwei Wang, Han Xiao, Yueqi Duan, Jie Zhou, Jiwen Lu
    IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI, IF: 24.31), 2022.
    [PDF] [Code]

    We propose the unsupervised binary descriptor learning method via dynamic bitwise interaction mining (D-GraphBit), where a graph convolutional network called GraphMiner reasons the optimal bitwise interaction for each input sample.

    dise Shapley-NAS: Discovering Operation Contribution for Neural Architecture Search
    Han Xiao, Ziwei Wang, Zheng Zhu, Jie Zhou, Jiwen Lu
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
    [PDF] [Supplement] [Code]

    We propose a Shapley value based method to evaluate operation contribution (Shapley-NAS) for neural architecture search.

    dise Generalizable Mixed-Precision Quantization via Attribution Rank Preservation
    Ziwei Wang, Han Xiao, Jiwen Lu, Jie Zhou
    IEEE International Conference on Computer Vision (ICCV), 2021.
    [PDF] [Supplement] [Code]

    We propose a generalizable mixed-precision quantization (GMPQ) method for efficient inference.

    dise Instance Similarity Learning for Unsupervised Feature Representation
    Ziwei Wang, Yunsong Wang, Ziyi Wu, Jiwen Lu, Jie Zhou
    IEEE International Conference on Computer Vision (ICCV), 2021.
    [PDF] [Supplement] [Code]

    We propose an instance similarity learning (ISL) method for unsupervised feature representation.

    dise Learning Efficient Binarized Object Detectors with Information Compression
    Ziwei Wang, Jiwen Lu, Ziyi Wu, Jie Zhou
    IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI, IF: 24.31), 2021, accepted.
    [PDF] [Supplement] [Code]

    We propose apresent binary neural networks with automatic information compression (AutoBiDet) to automatically adjust the IB trade-off according to the input complexity.

    dise Learning Channel-Wise Interactions for Binary Convolutional Neural Networks
    Ziwei Wang, Jiwen Lu, Jie Zhou
    IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI, IF: 24.31), 2021.
    [PDF] [Supplement][Code]

    We present a hierarchical channel-wise interaction based binary convolutional neural networks (HCI-BCNN) method to minimize the quantiztaion error for activations via hierarchical reinforcement learning.

    dise Deep Hashing with Active Pairwise Supervision
    Ziwei Wang, Quan Zheng, Jiwen Lu, Jie Zhou
    16th European Conference on Computer Vision (ECCV), 2020
    [PDF] [Supplement] [Slides] [Video]

    We propose a Deep Hashing method with Active Pairwise Supervision (DH-APS) to learn effective binary codes for image search with limited annotation budget.

    dise BiDet: An Efficient Binarized Object Detector
    Ziwei Wang, Ziyi Wu, Jiwen Lu, Jie Zhou
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020
    [PDF] [Code]

    We propose an efficient binarized object detector that fully utilizes the representational capacity of the binary neural networks by redundancy removal.

    dise Learning Channel-wise Interactions for Binary Convolutional Neural Networks
    Ziwei Wang, Jiwen Lu, Chenxin Tao, Jie Zhou
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019
    [PDF] [Code]

    We propose a channel-wise interaction based binary convolutional neural network learning method (CI-BCNN) for efficient inference with minimal information loss.

    dise Learning Deep Binary Descriptor with Multi-Quantization
    Yueqi Duan, Jiwen Lu, Ziwei Wang, Jianjiang Feng, Jie Zhou
    IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI, IF: 24.31), 2019.
    [PDF]

    We present a deep multi-quantization network to learn a data-dependent binarization for unsupervised features.

    dise GraphBit: Bitwise Interaction Mining via Deep Reinforcement Learning
    Yueqi Duan, Ziwei Wang, Jiwen Lu, Xudong Lin, Jie Zhou
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2018

    [PDF] [Code]

    We propose a GraphBit method to learn deep binary descriptors with enhanced reliability in a directed acyclic graph unsupervisedly.

    dise Learning Deep Binary Descriptor with Multi-Quantization
    Yueqi Duan, Jiwen Lu, Ziwei Wang, Jianjiang Feng, Jie Zhou
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2017

    [PDF]

    We present an unsupervised feature learning method called deep binary descriptor with multiquantization (DBD-MQ) for visual matching.

    Honors and Awards

  • 2020 National Scholarship
  • 2018 Chi-Sun Yeh Scholarship
  • 2016 Qualcomm Scholarship
  • Academic Services

  • Conference Reviewer: CVPR 2020/2021/2022, ICCV 2021, ECCV 2022, NeurIPS 2020/2021, ICML2021/2022, ICLR 2021/2022, IJCAI 2022, WACV 2020/2021/2022, ACCV 2020, ICME 2019/2020/2021/2022, ICPR 2018/2020, ICIP 2018/2019
  • Journal Reviewer: T-IP, T-CSVT, T-BIOM, Pattern Recognition Letters, JVIC

  • Website Template