Publications

Tutorials:

VALSE 2022 Keynote
[Website]
CVPR 2022 Workshop on the Art of Robustness
[Website]
VALSE 2021 Tutorial on Interpretable Machine Learning 
[Website]
世界人工智能大会(WAIC)可信AI论坛 Panel Discussion
[Website]
IJCAI 2021 Tutorial on Theoretically Unifying Conceptual Explanation and Generalization of DNNs
[Website] [Video]
IJCAI 2020 Tutorial on Trustworthiness of Interpretable Machine Learning
[Website] [Video]
ICML 2020 Online Panel Discussion: “Baidu AutoDL: Automated and Interpretable Deep Learning”
PRCV 2020 Tutorial on Robust and Explainable Artificial Intelligence

[Website]

Direction 1: Interpretability of Neural Networks & Deep Learning Theory
Conference papers

Where We Have Arrived in Proving the Emergence of Sparse Interaction Primitives in AI Models
Qihan Ren, Jiayang Gao, Wen Shen, Quanshi Zhang (Correspondence)
ICLR, 2024
[PDF]

Defining and Extracting generalizable interaction primitives from DNNs
Lu Chen*, Siyu Lou*, Benhao Huang, and Quanshi Zhang (Correspondence)
ICLR, 2024
[PDF]

Explaining Generalization Power of a DNN using Interactive Concepts
Huilin Zhou, Hao Zhang, Huiqi Deng, Dongrui Liu, Wen Shen, Shih-Han Chan, and Quanshi Zhang (Correspondence)
AAAI, 2024
[PDF]

Batch Normalization Is Blind to the First and Second Derivatives of the Loss
Zhanpeng Zhou*, Wen Shen*, Huixin Chen*, Ling Tang, Yuefeng Chen, and Quanshi Zhang (Correspondence)
AAAI, 2024
[PDF]

Clarifying the Behavior and the Difficulty of Adversarial Training
Xu Cheng, Hao Zhang, Yue Xin, Wen Shen, Jie Ren, and Quanshi Zhang (Correspondence)

AAAI, 2024
[PDF]

Towards the Difficulty for a Deep Neural Network to Learn Concepts of Different Complexities
Dongrui Liu*, Huiqi Deng*, Xu Cheng, Qihan Ren, Kangrui Wang, and Quanshi Zhang (Correspondence)

NeurIPS, 2023
[PDF]

Does a Neural Network Really Encode Symbolic Concept?
Mingjie Li, and Quanshi Zhang (Correspondence)

ICML, 2023
[PDF]

HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation
Lu Chen*, Siyu Lou*, Keyan Zhang, Jin Huang, Quanshi Zhang (Correspondence)

ICML, 2023
[PDF][Code]

Bayesian Neural Networks Avoid Encoding Perturbation-sensitive and Complex Concepts
Qihan Ren*, Huiqi Deng*, Yunuo Chen, Siyu Lou, and Quanshi Zhang (Correspondence)

ICML, 2023
[PDF]

Defects of Convolutional Decoder Networks in Frequency Representation
Ling Tang*, Wen Shen*, Zhanpeng Zhou, Yuefeng Chen, and Quanshi Zhang (Correspondence)

ICML, 2023
[PDF][Code]

Defining and Quantifying the Emergence of Sparse Concepts in DNNs
Jie Ren*, Mingjie Li*, Qirui Chen, Huiqi Deng, and Quanshi Zhang (Correspondence)
CVPR 2023
[PDF]

Can We Faithfully Represent Masked States to Compute Shapley Values on a DNN?
Jie Ren, Zhanpeng Zhou, Qirui Chen, and Quanshi Zhang (Correspondence)
ICLR 2023
[PDF][Code]

Quantification and Analysis of Layer-wise and Pixel-wise Information Discarding
Haotian Ma*, Hao Zhang*, Yinqing Zhang, Fan Zhou, and Quanshi Zhang (Correspondence)
ICML, 2022
[PDF][Code]

Towards Theoretical Analysis of Transformation Complexity of ReLU DNNs
Jie Ren*, Mingjie Li*, Meng Zhou, Shih-Han Chan, Quanshi Zhang (Correspondence)
ICML, 2022
[PDF][Code]

Discovering and Explaining the Representation Bottleneck of DNNs
Huiqi Deng, Qihan Ren, Hao Zhang, and Quanshi Zhang (Correspondence)
ICLR (Oral), 2022
[PDF][Code]

Exploring Image Regions Not Well Encoded by an INN
Zenan Ling, Fan Zhou, Meng Wei, and Quanshi Zhang (Correspondence)
AISTATS, 2022
[PDF]

Interpretable Generative Adversarial Networks
Chao Li (Correspondence), Kelu Yao, Jin Wang, Boyu Diao, Yongjun Xu, and Quanshi Zhang (Correspondence)
AAAI (Oral), 2022
[PDF]

A Unified Game-Theoretic Interpretation of Adversarial Robustness
Jie Ren*, Die Zhang*, Yisen Wang*, Lu Chen, Zhanpeng Zhou, Yiting Chen, Xu Cheng, Xin Wang, Meng Zhou, Jie Shi, and Quanshi Zhang (Correspondence)
Neurips, 2021
[PDF][Code]

Visualizing the Emergence of Intermediate Visual Patterns in DNNs
Mingjie Li, Shaobo Wang, and Quanshi Zhang (Correspondence)
Neurips, 2021
[PDF]

Interpreting Representation Quality of DNNs for 3D Point Cloud Processing
Wen ShenQihan RenDongrui Liu, and Quanshi Zhang (Correspondence)
Neurips, 2021
[PDF][Code]

Interpreting Attributions and Interactions of Adversarial Attacks
Xin Wang, Shuyun Lin, Hao Zhang, Yufei Zhu, and Quanshi Zhang (Correspondence)
ICCV, 2021
[PDF][Code]

Interpreting and Disentangling Feature Components of Various Complexity from DNNs
Jie Ren*, Mingjie Li*, Zexu Liu, and Quanshi Zhang (Correspondence)
ICML, 2021
[PDF][Code]

Interpretable Compositional Convolutional Neural Networks
Wen Shen*, Zhihua Wei*, Shikun Huang, Binbin Zhang, Jiaqi Fan, Ping Zhao, and Quanshi Zhang (Correspondence)
IJCAI, 2021
[PDF] [Code]

Verifiability and Predictability: Interpreting Utilities of Network Architectures for 3D Point Cloud Processing
Wen Shen*, Zhihua Wei*, Shikun Huang, Binbin Zhang, Panyue Chen, Ping Zhao, and Quanshi Zhang (Correspondence)

CVPR, 2021
[PDF][Code]

A Unified Approach to Interpreting and Boosting Adversarial Transferability
Xin Wang*, Jie Ren*, Shuyun Lin, Xiangming Zhu, Yisen Wang, Quanshi Zhang (Correspondence)
ICLR, 2021
[PDF] [Code]

Interpreting and Boosting Dropout from a Game-Theoretic View
Hao Zhang, Sen Li, Yinchao Ma, Mingjie Li, Yichen Xie, Quanshi Zhang (Correspondence)
ICLR, 2021
[PDF][Code]

Interpreting Multivariate Shapley Interactions in DNNs
Hao Zhang, Yichen Xie, Longjie Zheng, Die Zhang, and Quanshi Zhang (Correspondence)
AAAI, 2021
[PDF] [Code]

Building Interpretable Interaction Trees for Deep NLP Models
Die Zhang, Huilin Zhou, Hao Zhang, Xiaoyi Bao, Da Huo, Ruizhao Chen, Xu Cheng, Mengyue Wu, and Quanshi Zhang (Correspondence)
AAAI, 2021
[PDF] [Code]

3D-Rotation-Equivariant Quaternion Neural Networks
Binbin Zhang, Wen Shen, Shikun Huang, Zhihua Wei, and Quanshi Zhang (Correspondence)
ECCV, 2020
[PDF] [Code]

Explaining Knowledge Distillation by Quantifying the Knowledge
Xu Cheng, Zhefan Rao, Yilan Chen, and Quanshi Zhang (Correspondence)
CVPR 2020
[PDF]

Knowledge Consistency between Neural Networks and Beyond
Ruofan Liang, Tianlin Li, Longfei Li, Jing Wang, and Quanshi Zhang (Correspondence)
ICLR 2020
[PDF] [Code] [机器之心]

Interpretable Complex-Valued Neural Networks for Privacy Protection
Liyao Xiang, Hao Zhang, Haotian Ma, Yifan Zhang, Jie Ren, and Quanshi Zhang  (Correspondence)

ICLR 2020
[arXiv]

Explaining Neural Networks Semantically and Quantitatively
Runjin Chen, Hao Chen, Jie Ren, Ge Huang, Quanshi Zhang (Correspondence)

ICCV, 2019 (Oral)
[PDF]

Towards A Deep and Unified Understanding of Deep Neural Models in NLP
Chaoyu Guan, Xiting Wang, Quanshi Zhang (Correspondence), Runjin Chen, Di He, Xing Xie

ICML, 2019
[PDF] [Code]

Interpreting CNNs via Decision Trees
Quanshi Zhang, Yu Yang, Haotian Ma, and Ying Nian Wu

CVPR, 2019
[PDF]  [机器之心]

Unsupervised Learning of Neural Networks to Explain Neural Networks
Quanshi Zhang, Yu Yang, Yuchen Liu, Ying Nian Wu, and Song-Chun Zhu

Full paper in arXiv:1805.07468, 2018
Extended abstract in AAAI-19 Workshop on Network Interpretability for Deep Learning, 2019
[PDF]

Network Transplanting
Quanshi Zhang, Yu Yang, Qian Yu, Ying Nian Wu, and Song-Chun Zhu

Full paper in arXiv:1804.10272, 2018
Extended abstract in AAAI-19 Workshop on Network Interpretability for Deep Learning, 2019
[PDF]

Interpretable Convolutional Neural Networks
Quanshi Zhang
, Ying Nian Wu, and Song-Chun Zhu
CVPR (Spotlight) 2018
[PDF]  [Code]  [Project website]

Interpreting CNN Knowledge via an Explanatory Graph
Quanshi Zhang
, Ruiming Cao, Feng Shi, Ying Nian Wu, and Song-Chun Zhu

AAAI, 2018
[PDF]  [Code]  [Project website]  [Video]

Examining CNN Representations with respect to Dataset Bias
Quanshi Zhang, Wenguan Wang, and Song-Chun Zhu

AAAI, 2018
[PDF]

Mining Object Parts from CNNs via Active Question-Answering
Quanshi Zhang, Ruiming Cao, Ying Nian Wu, and Song-Chun Zhu

CVPR, 2017
[Project website]  [PDF]  [Video]

Growing Interpretable Part Graphs on ConvNets via Multi-Shot Learning
Quanshi Zhang, Ruiming Cao, Ying Nian Wu, and Song-Chun Zhu
AAAI, 2017
[PDF]  [Code]  [Project website]  [Video]

Journal papers

Unifying Fourteen Post-Hoc Attribution Methods With Taylor Interactions
Huiqi Deng, Na Zou, Mengnan Du, Weifu Chen, Guocan Feng, Ziwei Yang, Zheyang Li, Quanshi Zhang (Correspondence)
IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE T-PAMI), 2024
[PDF]

Interpretable Rotation-Equivariant Quaternion Neural Networks for 3D Point Cloud Processing
Wen Shen, Zhihua Wei, Qihan Ren, Binbin Zhang, Shikun Huang, Jiaqi Fan, and Quanshi Zhang (Correspondence)
IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE T-PAMI), 2024
[PDF]

Interpretability of Neural Networks Based on Game-Theoretic Interactions
Huilin Zhou, Jie Ren, Huiqi Deng, Xu Cheng, Jinpeng Zhang, and Quanshi Zhang (Correspondence)
Machine Intelligence Research, 2023
[PDF]

Quantifying the Knowledge in a DNN to Explain Knowledge Distillation for Classification
Quanshi Zhang* (Correspondence), Xu Cheng*, Yilan Chen, and Zhefan Rao

IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE T-PAMI), 2022
[PDF]

Interpretable CNNs for Object Classification
Quanshi Zhang
, Xin Wang, Ying Nian Wu, Huilin Zhou, and Song-Chun Zhu

IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE T-PAMI), 2020 (online available)
[PDF]  [Code]  [Project website]

Extraction of an Explanatory Graph to Interpret a CNN
Quanshi Zhang
, Xin Wang, Ruiming Cao, Ying Nian Wu, Feng Shi, and Song-Chun Zhu

IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE T-PAMI), 2020 (online available)
[PDF]  [Code]  [Project website]  [Video]

Mining Interpretable AOG Representations from Convolutional Networks via Active Question Answering
Quanshi Zhang, Jie Ren, Ge Huang, Ruiming Cao, Ying Nian Wu, and Song-Chun Zhu
IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE T-PAMI), 2020 (online available)
[PDF]

Visual interpretability for Deep Learning: a Survey
Quanshi Zhang and Song-Chun Zhu

Frontiers of Information Technology & Electronic Engineering. Vol. 19, No. 1, page 27-39, 2018 (best paper)
[PDF]  [Project website]  [机器之心]

arXiv papers

Proving Common Mechanisms Shared by Twelve Methods of Boosting Adversarial Transferability
Quanshi Zhang* (Correspondence), Xin Wang*, Jie Ren*, Xu Cheng, Shuyun Lin, Yisen Wang, Xiangming Zhu
arXiv:2207.11694, 2022
[PDF]

Trap of Feature Diversity in the Learning of MLPs
Dongrui Liu, Shaobo Wang, Jie Ren, Kangrui Wang, Sheng Yin, and Quanshi Zhang (Correspondence)
arXiv:2112.00980, 2021
[PDF]

Rapid Detection and Recognition of Whole Brain Activity in a Freely Behaving Caenorhabditis Elegans
Yuxiang Wu, Shang Wu, Xin Wang, Chengtian Lang, Quanshi Zhang, Quan Wen, and Tianqi Xu
arXiv:2109.10474, 2021
[PDF]

A Hypothesis for the Aesthetic Appreciation in Neural Networks
Xu Cheng, Xin Wang, Haotian Xue, Zhengyang Liang, and Quanshi Zhang (Correspondence)
arXiv:2108.02646, 2021
[PDF]

A Game-Theoretic Taxonomy of Visual Concepts in DNNs
Xu Cheng, Chuntung Chu, Yi Zheng, Jie Ren, and Quanshi Zhang (Correspondence)
arXiv:2106.10938, 2021
[PDF]

Rotation-Equivariant Neural Networks for Privacy Protection
Hao Zhang, Yiting Chen, Haotian Ma, Xu Cheng, Qihan Ren, Liyao Xiang, Jie Shi, and Quanshi Zhang
arXiv:2006.13016, 2020
[PDF]

Deep Quaternion Features for Privacy Protection
Hao Zhang, Yiting Chen, Liyao Xiang, Haotian Ma, Jie Shi, and Quanshi Zhang
arXiv:2003.08365, 2020
[PDF]

Towards a Unified Evaluation of Explanation Methods without Ground Truth
Hao Zhang, Jiayi Chen, Haotian Xue, and Quanshi Zhang
arXiv:1911.09017, 2019
[PDF]

Explaining AlphaGo: Interpreting Contextual Effects in Neural Networks
Zenan Ling, Haotian Ma, Yu Yang, Robert C. Qiu1, Song-Chun Zhu, and Quanshi Zhang
arXiv:1901.02184, 2019
[PDF]

Interactively Transferring CNN Patterns for Part Localization
Quanshi Zhang, Ruiming Cao, Shengming Zhang, Ying Nian Wu, and Song-Chun Zhu

arXiv:1708.01783, 2017
[PDF]

Direction 2: Graph mining & graph matching
Journal papers

Visual Graph Mining for Graph Matching
Quanshi Zhang, Xuan Song, Yu Yang, Haotian Ma, Ryosuke Shibasaki

Computer Vision and Image Understanding, vol. 178, page 16-29, 2019
[PDF]

Mining Deep And-Or Object Structures via Cost-Sensitive Question-Answer-Based Active Annotations
Quanshi Zhang, Ying Nian Wu, Hao Zhang, and Song-Chun Zhu

Computer Vision and Image Understanding, vol. 176-177, page 33-44, 2018
[PDF]

Object Discovery: Soft Attributed Graph Mining
Quanshi Zhang, Xuan Song, Xiaowei Shao, Huijing Zhao, and Ryosuke Shibasaki

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 38(3):532-545, 2016
[PDF]  [Project website]  [Code]

From RGB-D Images to RGB Images: Single Labeling for Mining Visual Models
Quanshi Zhang, Xuan Song, Xiaowei Shao, Ryosuke Shibasaki, Huijing Zhao

ACM Transactions on Intelligent Systems and Technology (ACM-TIST), 6(2): 16, 2015
[PDF]

Conference papers

Mining And-Or Graphs for Graph Matching and Object Discovery
Quanshi Zhang, Ying Nian Wu, and Song-Chun Zhu

ICCV, 2015
[PDF]  [Video]  [Supplementary]  [Project website]  [Code]

Attributed Graph Mining and Matching: An Attempt to Define and Extract Soft Attributed Patterns
Quanshi Zhang, Xuan Song, Xiaowei Shao, Huijing Zhao, and Ryosuke Shibasaki

CVPR, 2014
[PDF]  [Video]  [Project website]  [Video Spotlight]  [Code]

Learning Graph Matching: Oriented to Category Modeling from Cluttered Scenes
Quanshi Zhang, Xuan Song, Xiaowei Shao, Huijing Zhao, and Ryosuke Shibasaki

ICCV 2013
[PDF]

Category Modeling from just a Single Labeling: Use Depth Information to Guide the Learning of 2D Models
Quanshi Zhang, Xuan Song, Xiaowei Shao, Huijing Zhao, and Ryosuke Shibasaki

CVPR, 2013
[PDF]  [Video]

Direction 3: Other studies

Journal papers

Rapid Detection and Recognition of Whole Brain Activity in a Freely Behaving Caenorhabditis Elegans
Yuxiang Wu, Shang Wu, Xin Wang, Chengtian Lang, Quanshi Zhang, Quan Wen, and Tianqi Xu
PLOS Computational Biology, 2022
[PDF]

Prediction and Simulation of Human Mobility Following Natural Disasters
Xuan Song, Quanshi Zhang, Yoshihide Sekimoto, Ryosuke Shibasaki, Nicholas Jing Yuan, and Xing Xie

ACM Transactions on Intelligent Systems and Technology (ACM-TIST), 8(2): 29, 2016
[PDF]

Unsupervised Skeleton Extraction and Motion Capture from 3D Deformable Matching
Quanshi Zhang, Xuan Song, Xiaowei Shao, Ryosuke Shibasaki, and Huijing Zhao

Neurocomputing, Elsevier, pp.170-182, 2013
[PDF]  [Video]

Intelligent System for Human Behavior Analysis and Reasoning Following Large‐scale Disasters
Xuan Song, Quanshi Zhang, Yoshihide Sekimoto, Teerayut Horanont, Satoshi Ueyama, and Ryosuke Shibasaki

IEEE Intelligent Systems, vol. 28, no. 4, pp. 35-42, July-Aug. 2013
[PDF]

A Fully Online and Unsupervised System for Large and High Density Area Surveillance: Tracking, Semantic Scene Learning and Abnormality Detection
Xuan Song, Xiaowei Shao, Quanshi Zhang, Ryosuke Shibasaki, Huijing Zhao, Jinshi Cui, and Hongbin Zha

ACM Transactions on Intelligent Systems and Technology (ACMTIST), 4(2): 20, 2013
[PDF]

A Novel Dynamic Model for Multiple Pedestrians Tracking in Extremely Crowded Scenarios
Xuan Song, Xiaowei Shao, Quanshi Zhang, Ryosuke Shibasaki, Huijing Zhao, and Hongbin Zha

Information Fusion, Elsevier, 2012
[PDF]

arXiv papers

Conference papers

Learning to Prevent Input Leakages in the Mobile Cloud Inference
Liyao Xiang, Shuang Zhang, and Quanshi Zhang

IEEE Transactions on Mobile Computing, 2023
[PDF]

RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL
Jiexing Qi, Jingyao Tang, Ziwei He, Xiangpeng Wan, Yu Cheng, Chenghu Zhou, Xinbing Wang, Quanshi Zhang, and Zhouhan Lin

EMNLP, 2022
[PDF]

A Simulator of Human Emergency Mobility following Disasters: Knowledge Transfer from Big Disaster Data
Xuan Song, Quanshi Zhang, Yoshihide Sekimoto, Ryosuke Shibasaki, Nicholas Jing Yuan, and Xing Xie

AAAI, 2015
[PDF]

When 3D Reconstruction Meets Ubiquitous RGB-D Images
Quanshi Zhang, Xuan Song, Xiaowei Shao, Huijing Zhao, and Ryosuke Shibasaki

CVPR, 2014
[PDF]  [Video]  [Video spotlight]

Start from Minimum Labeling: Learning of 3D Object Models and Point Labeling from a Large and Complex Environment
Quanshi Zhang, Xuan Song, Xiaowei Shao, Huijing Zhao, and Ryosuke Shibasaki

ICRA, 2014
[PDF]  [Video]

Prediction of Human Emergency Behavior and their Mobility following Large-scale Disaster
Xuan Song, Quanshi Zhang, Yoshihide Sekimoto, and Ryosuke Shibasaki

KDD, 2014
[PDF]

Intelligent System for Urban Emergency Management During Large-scale Disaster
Xuan Song, Quanshi Zhang, Yoshihide Sekimoto, and Ryosuke Shibasaki

AAAI, 2014
[PDF]

Unsupervised 3D Category Discovery and Point Labeling from a Large Urban Environment
Quanshi Zhang, Xuan Song, Xiaowei Shao, Huijing Zhao, and Ryosuke Shibasaki

ICRA, 2013
[PDF]  [Video]  [PPT]

Modeling and Probabilistic Reasoning of Population Evacuation During Large-scale Disaster
Xuan Song, Quanshi Zhang, Yoshihide Sekimoto, Teerayut Horanont, Satoshi Ueyama, and Ryosuke Shibasaki

KDD, 2013
[PDF]

Laser-based Intelligent Surveillance and Abnormality Detection in Extremely Crowded Scenarios
Xuan Song, Xiaowei Shao, Quanshi Zhang, Ryosuke Shibasaki, Huijing Zhao, and Hongbin Zha

ICRA, 2012
[PDF]

Moving Object Classification using Horizontal Laser Scan Data
Huijing Zhao, Quanshi Zhang, Masaki Chiba, Ryosuke Shibasaki, Jinshi Cui, and Hongbin Zha

ICRA, 2009
[PDF]