Zhaofei Yu
|
|
Biography
I'm an Assistant Professor of the School of Artificial Intelligence at Peking University, and I am heading the Brain-inspired Vision Lab. I received the B.S. degree from the Hong Shen Honors School, College of Optoelectronic Engineering, Chongqing University, China, in 2012 and the Ph.D. degree from the Automation Department, Tsinghua University, China, in 2017. From Sep. 2015 to Sep. 2016, I visited Prof. Wolfgang Maass's group at Graz University of Technology as a visiting student.
Research Interests
My research interests cover biological and computer vision, neuromorphic computation, and computational neuroscience. I am interested in learning and inference of spiking neural networks, and vision information processing based on neuromorphic visual sensors. I am also interested in extracting meaningful information embedded in high-dimensional neuroscience data and explaining how the visual system implements encoding and decoding.
Opening
- We are looking for highly motivated students to join our group. Our group has opening positions for Ph.D. and Undergraduate Internship. If you are interested in researching on brain-like computing, please send me an email with your CV.
- We are hiring highly motivated postdocs to join our group through the Boya Postdoctoral Fellowship at Peking University. Please send an email with your CV and Research Statement.
News
- [2023.03] One paper was accepted by CVPR 2023. Congratulations to Tong Bu!
- [2023.01] Two papers were accepted by ICLR 2023. Congratulations to Yanqi and Zecheng!
- [2023.01] One paper was accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence. Congratulations to Yajing!
- [2022.11] Three papers were accepted by AAAI 2023. Congratulations to Zecheng, Jiyuan, Shanshan, and Shiyan!
- [2022.10] One paper was accepted by IEEE Transactions on Image Processing. Congratulations to Yajing!
- [2022.09] Congratulate Shanshan Jia for the National Scholarship!
- [2022.09] Four papers were accepted by NeurIPS 2022. Congratulations to Jianhao, Yaoyu, Chaoteng, Rui Zhao, Tong Bu, and Wei Fang!
- [2022.07] One paper was accepted by ECCV 2022. Congratulations to Jiyuan!
- [2022.07] Congratulate Tong Bu for "Top Ten Best Undergraduate Thesis"!
- [2022.05] One paper was accepted by ICML 2022. Congratulations to Yanqi!
- [2022.04] One paper was accepted by IJCAI 2022. Congratulations to Shiyan!
- [2022.01] One paper was accepted by ICASSP 2022. Congratulations to Junwei!
- [2022.01] One paper was accepted by ICLR 2022. Congratulations to Bu Tong!
- [2022.01] One paper on Vidar camera was accepted by Engineering!
- [2021.12] One paper was accepted by Neural Computation. Congratulations to Yijun!
- [2021.12] One paper was accepted by IEEE Transactions on Computational Imaging. Congratulations to Zhao Jing!
- [2021.12] One paper on the dimensionality reduction of neural spikes was accepted by Cell Patterns! Congratulations to Shanshan!
- [2021.12] Two papers were accepted by AAAI 2022. Congratulations to Ding Gang and Bu Tong!
- [2021.11] One paper on dissecting dynamical circuits of the brain was accepted by PLOS Computational Biology! Congratulations to Shanshan!
- [2021.09] One paper on learning of SNNs was accepted by NeurIPS 2021. Congratulations to Fang Wei!
- [2021.08] One paper on visual neural coding was accepted by Cell patterns! Congratulations to Yajing!
- [2021.07] Two papers were accepted by ICCV 2021. Congratulations to Fang Wei and Zhao Jing!
- [2021.04] Two papers were accepted by IJCAI 2021. Congratulations to Jianhao and Yanqi!
- [2021.03] One paper was accepted by CVPR 2021. Congratulations to Yajing!
- [2021.01] One papers was accepted by IEEE Transactions on Cybernetics. Congratulations to Shanshan!
Publications
In press
2023
-
Capture the Moment: High-speed Imaging with Spiking Cameras through Short-term Plasticity
Yajing Zheng, Lingxiao Zheng, Zhaofei Yu*, Tiejun Huang, Song Wang
IEEE Transactions on Pattern Analysis and Machine Intelligence [pdf] -
1000× Faster Camera and Machine Vision with Ordinary Devices
Tiejun Huang, Yajing Zheng, Zhaofei Yu*, Rui Chen, Yuan Li, Ruiqin Xiong, Lei Ma, Junwei Zhao, Siwei Dong, Lin Zhu,
Jianing Li, Shanshan Jia, Yihua Fu, Boxin Shi, Si Wu, and Yonghong Tian
Engineering [pdf] -
Spike-Based Motion Estimation for Object Tracking Through Bio-Inspired Unsupervised Learning
Yajing Zheng, Zhaofei Yu*, Song Wang, Tiejun Huang
IEEE Transactions on Image Processing [pdf] -
Asynchronous Spatiotemporal Spike Metric for Event Cameras
Jianing Li, Yihua Fu, Siwei Dong, Zhaofei Yu, Tiejun Huang, Yonghong Tian*
IEEE Transactions on Neural Networks and Learning Systems [pdf] -
Deep Spike Learning with Local Classifiers
Chenxiang Ma, Rui Yan, Zhaofei Yu, Qiang Yu
IEEE Transactions on Cybernetics [pdf] -
Spike Calibration: Bridging the Gap between ANNs and SNNs in ANN-SNN Conversion
Zecheng Hao, Jianhao Ding, Tong Bu, Tiejun Huang, Zhaofei Yu*
ICLR [pdf] -
A Unified Framework of Soft Threshold Pruning
Yanqi Chen, Zhaofei Yu, Wei Fang, Zhengyu Ma, Xiawu Zheng, Yonghong Tian*
ICLR [pdf] -
Reducing ANN-SNN Conversion Error through Residual Membrane Potential
Zecheng Hao, Tong Bu, Jianhao Ding, Tiejun Huang, Zhaofei Yu*
AAAI (oral) [pdf] -
Learning Temporal-ordered Representation for Spike Streams Based on Discrete Wavelet Transforms
Jiyuan Zhang†, Shanshan Jia†, Zhaofei Yu*, Tiejun Huang
AAAI [pdf] -
Self-Supervised Joint Dynamic Scene Reconstruction and Optical Flow Estimation for Spiking Camera
Shiyan Chen, Zhaofei Yu*, Tiejun Huang
AAAI [pdf]
2022
-
Zooming in on the Brain via Data Science
Shanshan Jia, Zhaofei Yu*
Cell Patterns [pdf] -
Representing the Dynamics of High-Dimensional Data with Non-Redundant Wavelets
Shanshan Jia, Xingyi Li, Tiejun Huang, Jian K. Liu*, Zhaofei Yu*
Cell Patterns [pdf] [code] -
Decoding Pixel-Level Image Features from Two-Photon Calcium Signals of Macaque Visual Cortex
Yijun Zhang, Tong Bu, Jiyuan Zhang, Shiming Tang, Zhaofei Yu*, Jian K. Liu, Tiejun Huang
Neural Computation [pdf] -
Revealing Fine Structures of the Retinal Receptive Field by Deep Learning Networks
Qi Yan†, Yajing Zheng†, Shanshan Jia, Zhaofei Yu*, Feng Chen, Yonghong Tian, Tiejun Huang, Jian K. Liu*
IEEE Transactions on Cybernetics [pdf] -
Reconstructing Clear Image for High-Speed Motion Scene With a Retina-Inspired Spike Camera
Jing Zhao, Ruiqin Xiong*, Jiyu Xie, Boxin Shi, Zhaofei Yu, Wen Gao, Tiejun Huang
IEEE Transactions on Computational Imaging [pdf] -
Neural System Identification with Spike-Triggered Non-Negative Matrix Factorization
Shanshan Jia, Zhaofei Yu*, Arno Onken, Yonghong Tian, Tiejun Huang, Jian K. Liu*
IEEE Transactions on Cybernetics [pdf] -
A Probabilistic Approach for Cooperative Computation Offloading in MEC-Assisted Vehicular Networks
Penglin Dai, Kaiwen Hu, Xiao Wu, Huanlai Xing, Fei Teng, Zhaofei Yu
IEEE Transactions on Intelligent Transportation Systems [pdf] -
Neural Decoding of Visual Information Across Different Neural Recording Modalities and Approaches
Yijun Zhang, Zhaofei Yu*, Jian K. Liu, Tiejun Huang
Machine Intelligence Research [pdf] -
SNN-RAT: Robustness-enhanced Spiking Neural Network through Regularized Adversarial
Jianhao Ding, Tong Bu, Zhaofei Yu*, Jian K. Liu, Tiejun Huang
NeurIPS (Spotlight) [pdf] [code] -
Training Spiking Neural Networks with Event-driven Backpropagation
Yaoyu Zhu, Zhaofei Yu*, Wei Fang, Xiaodong Xie, Tiejun Huang, Timothée Masquelier
NeurIPS (Spotlight) [pdf][code] -
Temporal Effective Batch Normalization in Spiking Neural Networks
Chaoteng Duan†, Jianhao Ding†, Shiyan Chen, Zhaofei Yu*, Tiejun Huang
NeurIPS [pdf] -
Learning Optical Flow From Continuous Spike Streams
Rui Zhao, Ruiqin Xiong*, Jing Zhao, Zhaofei Yu, Xiaopeng Fan, Tiejun Huang
NeurIPS [pdf] [code] -
Spike Transformer: Monocular Depth Estimation for Spiking Camera
Jiyuan Zhang, Lulu Tang, Zhaofei Yu*, Jiwen Lu, Tiejun Huang
ECCV [pdf] -
State Transition of Dendritic Spines Improves Learning of Sparse Spiking Neural Networks
Yanqi Chen, Zhaofei Yu*, Wei Fang, Zhengyu Ma, Tiejun Huang, Yonghong Tian*
ICML [pdf] -
Self-Supervised Mutual Learning for Dynamic Scene Reconstruction of Spiking Camera
Shiyan Chen, Chaoteng Duan, Zhaofei Yu*, Ruiqin Xiong, Tiejun Huang
IJCAI [pdf] -
SpikingSIM: A Bio-Inspired Spiking Simulator
Junwei Zhao, Shiliang Zhang, Lei Ma, Zhaofei Yu, Tiejun Huang
ISCAS [pdf] -
Modeling the Detection Capability of High-Speed Spiking Cameras
Junwei Zhao, Zhaofei Yu*, Lei Ma*, Ziluo Ding, Shiliang Zhang, Yonghong Tian, Tiejun Huang
ICASSP [pdf] -
Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networks
Tong Bu, Wei Fang, Jianhao Ding, Penglin Dai, Zhaofei Yu*, Tiejun Huang
ICLR [pdf] -
Spatio-Temporal Recurrent Networks for Event-Based Optical Flow Estimation
Ziluo Ding, Rui Zhao, Jiyuan Zhang, Tianxiao Gao, Ruiqin Xiong, Zhaofei Yu*, Tiejun Huang
AAAI [pdf] -
Optimized Potential Initialization for Low-latency Spiking Neural Networks
Tong Bu, Jianhao Ding, Zhaofei Yu*, Tiejun Huang
AAAI [pdf]
2021
-
Dissecting Cascade Computational Components in Spiking Neural Networks
Shanshan Jia, Dajun Xing, Zhaofei Yu*, Jian K. Liu*
PLoS Computational Biology [pdf] -
Unraveling Neural Coding of Dynamic Natural Visual Scenes via Convolutional Recurrent Neural Networks
Yajing Zheng, Shanshan Jia, Zhaofei Yu*, Jian K. Liu*, Tiejun Huang
Cell Patterns [pdf] -
Deep Residual Learning in Spiking Neural Networks
Wei Fang, Zhaofei Yu*, Yanqi Chen, Tiejun Huang, Timothee Masquelier, Yonghong Tian*
NeurIPS [pdf] -
Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks
Wei Fang, Zhaofei Yu*, Yanqi Chen, Timothee Masquelier, Tiejun Huang, Yonghong Tian*
ICCV [pdf] -
Super Resolve Dynamic Scene From Continuous Spike Streams
Jing Zhao, Jiyu Xie, Ruiqin Xiong*, Jian Zhang, Zhaofei Yu, Tiejun Huang
ICCV [pdf] -
Optimal ANN-SNN Conversion for Fast and Accurate Inference in Deep Spiking Neural Networks
Jianhao Ding, Zhaofei Yu*, Yonghong Tian*, Tiejun Huang
IJCAI [pdf] -
Pruning of Deep Spiking Neural Networks through Gradient Rewiring
Yanqi Chen, Zhaofei Yu*, Wei Fang, Tiejun Huang, Yonghong Tian*
IJCAI [pdf] -
High-Speed Image Reconstruction Through Short-Term Plasticity for Spiking Cameras
Yajing Zheng†, Lingxiao Zheng†, Zhaofei Yu*, Boxin Shi, Yonghong Tian, Tiejun Huang
CVPR [pdf] -
Asynchronous Deep Reinforcement Learning for Data-Driven Task Offloading in MEC-Empowered Vehicular Networks
Penglin Dai*, Kaiwen Hu, Xiao Wu, Huanlai Xing, Zhaofei Yu
INFOCOM [pdf]
2020
-
Towards the Next Generation of Neuroprosthesis: Computation with Spikes
Zhaofei Yu, Jian K. Liu*, Shanshan Jia, Yicheng Zhang, Yajing Zheng, Yonghong Tian, Tiejun Huang
Engineering [pdf] -
Emergent Inference of Hidden Markov Models in Spiking Neural Networks through Winner-Take-All
Zhaofei Yu†, Shangqi Guo†, Fei Deng, Qi Yan, Keke Huang, Jian K. Liu*, Feng Chen*
IEEE Transactions on Cybernetics [pdf] -
Sampling-tree Model：Efficient Implement of Distributed Bayesian Inference in Neural Networks
Zhaofei Yu, Feng Chen*, Jian K. Liu*
IEEE Transactions on Cognitive and Developmental Systems [pdf] -
Probabilistic Inference of Binary Markov Random Fields in Spiking Neural Networks through Mean-field Approximation
Yajing Zheng, Shanshan Jia, Zhaofei Yu*, Tiejun Huang, Jian K. Liu, Yonghong Tian*
Neural Networks [pdf] -
Reconstruction of Natural Visual Scenes from Neural Spikes with Deep Neural Networks
Yicheng Zhang, Shanshan Jia, Yajing Zheng, Zhaofei Yu*, Yonghong Tian, Siwei Ma, Tiejun Huang, Jian K. Liu*
Neural Networks [pdf] -
Intrinsic and Synaptic Properties Shaping Diverse Behaviors of Neural Dynamics
Lingling An*, Yuanhong Tang, Doudou Wang, Shanshan Jia, Qingqi Pei, Quan Wang, Zhaofei Yu*, Jian K. Liu
Frontiers in Computational Neuroscience [pdf] -
Noise Helps Optimization Escape from Saddle Points in the Synaptic Plasticity
Ying Fang, Zhaofei Yu, Feng Chen*
Frontiers in Neuroscience [pdf] -
SDARE: A Stacked Denoising Autoencoder Method for Game Dynamics Network Structure Reconstruction
Keke Huang, Shuo Li, Penglin Dai, Zhen Wang, Zhaofei Yu*
Neural Networks [pdf] -
Network Structure Reconstruction with Symmetry Constraint
Zihua Hang, Penglin Dai*, Shanshan Jia*, Zhaofei Yu
Chaos, Solitons & Fractals [pdf]