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 20 scientific papers in the IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Robotics and Automation Letters, CVPR, ICCV, ECCV, IROS and ICRA.
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, ICRA, WACV, ACCV, ICPR, ICME and ICIP.
Email  / 
CV  / 
Google Scholar  / 
Github
|
|
News
2023-03: One paper on AutoML is accepted to IJCV.
2023-02: One paper on binary sparse convolutional networks is accepted to CVPR 2023.
2023-02: One paper on binary neural networks is accepted to Acta Electonica Sinica(电子学报).
2023-01: One paper on object shape estimation is accepted to ICRA 2023.
2022-12: One paper on vision transformer quantization is accepted to TPAMI.
2022-10: One paper on robotic packing is accepted to RAL.
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.
|
|
Learning Accurate Performance Predictors for Ultrafast Automated Model Compression
Ziwei Wang, Jiwen Lu, Han Xiao, Shengyu Liu, Jie Zhou
International Journal of Computer Vision (IJCV, IF: 13.37), 2023.
[PDF]
[Code]
We propose an ultrafast auto- mated model compression framework for flexible network deployment, where we can obtain the optimal compression policy within several seconds.
|
|
Binarizing Sparse Convolutional Networks for Efficient Point Cloud Analysis
Xiuwei Xu, Ziwei Wang, Jie Zhou, Jiwen Lu
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
[PDF]
we propose binary sparse convolutional networks for efficient point cloud analysis, where we search the optimal subset of convolution operation that activates the sparse convolution at various locations for quantization error alleviation.
|
|
Category-level Shape Estimation for Densely Cluttered Objects
Zhenyu Wu, Ziwei Wang, Jiwen Lu, Haibin Yan
IEEE International Conference on Robotics and Automation (ICRA), 2023.
[PDF]
[Code]
We propose a category-level shape estimation method for densely cluttered objects, which addresses the challenges of large object segmentation errors and inaccurate shape recovery on unseen instances.
|
|
Quantformer: Learning Extremely Low-precision Vision Transformers
Ziwei Wang, Changyuan Wang, Xiuwei Xu, Jie Zhou, Jiwen Lu
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI, IF: 24.31), 2022.
[PDF]
[Supp]
[Code]
We propose the extremely low-precision vision transformers in 2-4 bits, where the self-attention rank consistency and group-wise quantization are presented for quantization error minimization.
|
|
Planning Irregular Object Packing via Hierarchical Reinforcement Learning
Sichao Huang, Ziwei Wang, Jie Zhou, Jiwen Lu
IEEE Robotics and Automation Letters (RAL), 2022
[PDF]
[Robot Demo]
[Simulation Demo]
[Code]
we develop a packing planning method for general objects including the packing sequence, locations and orientations to maximize the space utilization ratio.
|
|
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.
|
|
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.
|
|
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.
|
|
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.
|
|
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.
|
|
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.
|
|
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.
|
|
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), 2022.
[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.
|
|
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.
|
|
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.
|
|
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.
|
|
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.
|
|
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.
|
|
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.
|
|
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
2022 National Scholarship
2020 National Scholarship
2018 Chi-Sun Yeh Scholarship
2016 Qualcomm Scholarship
|
Academic Services
Conference Reviewer: CVPR 2020/2021/2022/2023, ICCV 2021, ECCV 2022, NeurIPS 2020/2021/2022, ICML2021/2022/2023, ICLR 2021/2022/2023, IJCAI 2022, ICRA 2023
Journal Reviewer: T-IP, T-CSVT, T-BIOM, Pattern Recognition Letters, JVIC
|
|