About
I am a Lecturer at the Complex Laboratory of New Finace and Economics (NiceLab), Southwestern University of Finance and Economics (SWUFE).
Prior to this, I obtained a BSc degree with in Information and Computing Science from the Yantai University, in 2017, and the Ph.D. degree in computer science from the University of Electronic Science and Technology of China, in 2024, advised by Prof. Guisong Liu.
My current research focuses on investigating in brain-inspired computing, specifically, event-camera based multimodal visual fusion, as well as the spiking neural network models and their learning mechanisms. I have published papers at the top international AI journals and conferences (IEEE TIP, IEEE TNNLS, IEEE TCYB, CVPR, AAAI, etc.). I also serve as reviewers for AI journals and conferences (IEEE TCSVT, IEEE TNNLS, KBS, ICML, CVPR, ACM MM, IJCAI, AAAI, etc.).
Selected Publications
View All →SFedCA: Credit Assignment-Based Active Client Selection Strategy for Spiking Federated Learning
Qiugang Zhan, Jinbo Cao, Xiurui Xie†, Huajin Tang, Malu Zhang, Shantian Yang, Guisong Liu†
IEEE Transactions on Neural Networks and Learning Systems
We propose an active client selection method for spiking federated learning. This method assign credit for clients according to the firing intensity changes.
A two-stage spiking meta-learning method for few-shot classification
Qiugang Zhan, Bingchao Wang, Anning Jiang, Xiurui Xie, Malu Zhang, Guisong Liu†
Knowledge-Based Systems
We explore a two-stage metric-based SNN meta-learning framework. During pre-training, a CESM model is trained to extract image features. In the meta-training stage, the MESM model employs the CKA method to measure the similarity between these learned features for meta-learning.
Spiking Transfer Learning From RGB Image to Neuromorphic Event Stream
Qiugang Zhan, Guisong Liu†, Xiurui Xie†, Ran Tao, Malu Zhang, Huajin Tang
IEEE Transactions on Image Processing
To take advantage of both the rich knowledge in labeled RGB images and the features of the event camera, we propose a transfer learning method from the RGB to the event domain.
Bio-inspired Active Learning method in spiking neural network
Qiugang Zhan, Guisong Liu†, Xiurui Xie†, Malu Zhang, Guolin Sun
Knowledge-Based Systems
We propose an effective Bio-inspired Active Learning (BAL) method to reduce the training cost of SNN models. Bio-inspired behavior patterns of spiking neurons are defined to represent the internal states of SNN models for active learning.
Effective Transfer Learning Algorithm in Spiking Neural Networks
Qiugang Zhan, Guisong Liu†, Xiurui Xie, Guolin Sun, Huajin Tang
IEEE Transactions on Cybernetics
We propose the first transfer learning framework in SNN, and the rationality of centered kernel alignment (CKA) as a domain distance measurement relative to maximum mean discrepancy (MMD) in deep SNNs.
News
Our work has been accepted by CVPR 2026! 🎉 Title: Sparsely Timing the Change: A Spiking Temporal Framework for Remote Sensing Interpretation
Our work has been accepted by IEEE TNNLS! 🎉