Xiaojie Li (李潇婕)

I am Xiaojie Li, a third-year Ph.D. candidate at the School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen). I am supervised by Prof. Liqiang Nie and Prof. Min Zhang, and I collaborate closely with Prof. Jianlong Wu and Prof. Yue Yu. Prior to my Ph.D., I worked as an Assistant Research Manager at SenseTime from 2019 to 2022, collaborating with Fei Wang and Chen Qian. I received my Bachelor’s and Master’s degrees from the School of Instrumentation and Optoelectronic Engineering at Beihang University in 2016 and 2019, under the supervision of Prof. Fuqiang Zhou. My research interests include Computer Vision, Self-supervised Learning, Multi-modal Learning, Continual Learning, and Knowledge Distillation.

xiaojieli0903@gmail.com Google Scholar

News

[2024/09] One paper accepted by NeurIPS 2024.
[2024/07] One first-author paper accepted by ECCV 2024.
[2024/05] One paper accepted by ICML 2024.
[2023/08] Two first-author papers accepted by ACM MM 2023.

Publications

(* denotes equal contributions and ^ denotes corresponding author)

Preprint

Continuous Knowledge-Preserving Decomposition for Few-Shot Continual Learning
Xiaojie Li, Yibo Yang, Jianlong Wu, David A. Clifton, Yue Yu, Bernard Ghanem, Min Zhang
[PDF] [Code]

Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning
Xiaojie Li, Yibo Yang, Jianlong Wu, Bernard Ghanem, Liqiang Nie, Min Zhang
[PDF] [Code]

2024

CorDA: Context-Oriented Decomposition Adaptation of Large Language Models
Yibo Yang, Xiaojie Li, Zhongzhu Zhou, Shuaiwen Leon Song, Jianlong Wu, Liqiang Nie^, Bernard Ghanem^
Advances in Neural Information Processing Systems (NeurIPS), 2024
[PDF] [Code]

GenView: Enhancing View Quality with a Pretrained Generative Model for Self-Supervised Learning
Xiaojie Li, Yibo Yang^, Xiangtai Li, Jianlong Wu^, Yue Yu, Bernard Ghanem, Min Zhang
European Conference on Computer Vision (ECCV), 2024
[PDF] [Code]

Towards Interpretable Deep Local Learning with Successive Gradient Reconciliation
Yibo Yang^, Xiaojie Li, Motasem Alfarra, Hasan Hammoud, Adel Bibi, Philip Torr, Bernard Ghanem
International Conference on Machine Learning (ICML), 2024
[PDF]

2023

Fine-grained Key-Value Memory Enhanced Predictor for Video Representation Learning
Xiaojie Li, Jianlong Wu^, Shaowei He, Kang Shuo, Yue Yu, Liqiang Nie, Min Zhang
ACM Conference on Multimedia (ACM MM), 2023
[PDF] [Code]

Mask Again: Masked Knowledge Distillation for Masked Video Modeling
Xiaojie Li, Shaowei He, Jianlong Wu^, Yue Yu, Liqiang Nie^, Min Zhang
ACM Conference on Multimedia (ACM MM), 2023
[PDF] [Code]

2022

HEAD: HEtero-Assists Distillation for Heterogeneous Object Detectors
Luting Wang, Xiaojie Li, Yue Liao^, Zeren Jiang, Jianlong Wu, Fei Wang, Chen Qian, Si Liu^
European Conference on Computer Vision (ECCV), 2022
[PDF] [Code]

2020

Local Correlation Consistency for Knowledge Distillation
Xiaojie Li, Jianlong Wu^, Hongyu Fang, Yue Liao, Fei Wang, Chen Qian
European Conference on Computer Vision (ECCV), 2020
[PDF]

Agree to Disagree: Adaptive Ensemble Knowledge Distillation in Gradient Space
Shangchen Du*, Shan You*^, Xiaojie Li, Jianlong Wu, Fei Wang, Chen Qian, Changshui Zhang
Advances in Neural Information Processing Systems (NeurIPS), 2020
[PDF]

2018

Detector-in-Detector: Multi-level Analysis for Human-Parts.
Xiaojie Li, Lu Yang, Qing Song, Fuqiang Zhou^.
Asia Conference on Computer Vision (ACCV), 2018
[PDF]

High-Frequency Details Enhancing DenseNet for Super-Resolution.
Fuqiang Zhou^, Xiaojie Li, Zuoxin Li.
Neurocomputing, 2018
[PDF]

Academic Services

Reviewer for Journals:
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), Pattern Recognition (PR)

Reviewer for Conferences:
Neural Information Processing Systems (NeurIPS), IEEE Conference on Computer Vision and Pattern Recognition (CVPR), ACM Conference on Multimedia (ACM MM), International Conference on Learning Representation (ICLR)

Education

Harbin Institute of Technology (Shenzhen), Shenzhen, China
Sep. 2022 – Present
Ph.D. in Computer Science and Technology
Advisor: Prof. Liqiang Nie, Prof. Min Zhang

Beihang University, Beijing, China
Sep. 2016 – Feb. 2019
M.E. in Instrumentation and Optoelectronic Engineering
Advisor: Prof. Fuqiang Zhou

Beihang University, Beijing, China
Sep. 2012 – Jun. 2016
B.E. in Instrumentation and Optoelectronic Engineering

Awards

2024 China National Scholarship
2019 Excellent Graduate of Beijing
2019 Excellent Graduate Thesis of Beihang University
2018 China National Scholarship