Linfeng Zhang
ArchipLab, Supervised by Kaisheng Ma
Interdisciplinary Information Sciences (IIIS)
Tsinghua University
zhanglinfeng1997@outlook.com

Unsplashed background img 1


About Me

I’m Linfeng Zhang from Tsinghua University, Institute for Interdisciplinary Information Sciences (IIIS). I get my Bachelor degree in Northeastern University, School of Computer Science in 2019. Currently I’m a Phd candidate supervised by Kaisheng Ma. My major research interest is to improve the effectiveness and efficiency of deep neural networks via knowledge distillation. In 2019, I firstly propose the idea of self-distillation. So far, I have also successfully applied knowledge distillation to all kinds of tasks, such as 2D classification detection, segmentation, image-to-image translation, video recognition, point cloud-based detection, BEV based multi-view detection, representation and so on. Please refer to my CV for more information.

I plan to get my Phd degree in 06/2024 and I’m looking forward to opportunities of internship and jobs now

News
  •   • 01 / 2023:   One paper was accepted by ICLR2023.
  •   • 12 / 2022:   I was granted with Jiangnanxiang Scholarship （蒋南翔奖学金）(top-10 in Tsinghua University).
  •   • 10 / 2022:   One paper is accepted by IEE TCSVT
  •   • 10 / 2022:   I was granted with Microsoft Scholarship（微软学者奖学金） (top-10 in Asian).
  •   • 07 / 2022:   One paper is accepted by ECCV2022 as oral presentation.
  •   • 03 / 2022:   One paper is accepted by CVPR2022
  •   • 10 / 2021:   I was granted with Tanglixin Scholarship（唐立新奖学金） (2% in Tsinghua University).
  •   • 06 / 2021:   One paper is accepted by MobiCom2021
  •   • 04 / 2021:   One paper is accepted by IJCNN2021
  •   • 03 / 2021:   One paper is accepted by IEEE TPAMI
  •   • 01 / 2021:   One paper is accepted by ICLR2021
  •   • 10 / 2020:   I was granted with National Scholarship（国家奖学金） (2% in Tsinghua University).
  •   • 09 / 2020:   One paper is accepted by NeurIPS2020
  •   • 03 / 2020:   One paper is accepted by CVPR2020
  •   • 09 / 2019:   One paper is accepted by NeurIPS 2019
  •   • 07 / 2019:   One paper is accepted by ICCV 2019
  •   • 07 / 2019:   I obtained my bachelor degree from Northeastern University and get the award of Outstanding Graduation Dissertation (<2%).
Publications
Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation.
Linfeng Zhang, Jiebo Song, Anni Gao, Jingwei Chen, Chenglong Bao, and Kaisheng Ma
IEEE International Conference on Computer Vision (ICCV2019).
SCAN: A Scalable Neural Networks Framework Towards Compact and Efficient Models
Linfeng Zhang, , Zhanhong Tan, Jiebo Song, Jingwei Chen, Chenglong Bao, and Kaisheng Ma.
Neural Information Processing Systems (NeurIPS2019)
Auxiliary Training: Towards Accurate and Robust Models
Linfeng Zhang, Muzhou Yu, Tong Chen, Zuoqiang Shi, Chenglong Bao, and Kaisheng Ma
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR2020)
Task-Oriented Feature Distillation
Linfeng Zhang, Yukang Shi, Zuoqiang Shi, Kaisheng Ma, and Chenglong Bao
Neural Information Processing Systems (NeurIPS2020).
Self-Distillation: Towards Efficient and Compact Neural Networks
Linfeng Zhang, Chenglong Bao, and Kaisheng Ma
IEEE Transactions of Pattern Analysis and Machine Intelligence (IEEE TPAMI)
Improve Object Detection with Feature-based Knowledge Distillation: Towards Accurate and Efficient Detectors
Cheng Chi*, Linfeng Zhang, Kaisheng Ma
The International Conference on Learning Representations (ICLR2021)
Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translation
Linfeng Zhang, Xin Chen, Xiaobing Tu, Pengfei Wan, Ning Xu, Kaisheng Ma
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR2022)
Contrastive Deep Supervision
Linfeng Zhang, Xin Chen, Junbo Zhang, Runpei Dong, Kaisheng Ma
European Conference on Computer Vision Oral Presentation
Pointdistiller: structured knowledge distillation towards efficient and compact 3d detection
Linfeng Zhang, Runpei Dong, Huang-Shuo Tai Kaisheng Ma
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR2023)
A Good Data Augmentation Policy Is Not All You Need: A Multi-Task Learning Perspective
Linfeng Zhang, Kaisheng Ma
IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT)
Fine-grained emotion classification of Chinese microblogs based on graph convolution networks
Yuni Lai, Linfeng Zhang(equal contribution), Donghong Han, Rui Zhou, Guoren Wang
World Wide Web Journal
Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks
Runpei Dong, Zhanhong Tan, Mengdi Wu, Linfeng Zhang, Kaisheng Ma
International Conference on Machine Learning (ICML2022)
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?
Runpei Dong, Zekun Qi, Linfeng Zhang, Junbo Zhang, Jianjian Sun, Zheng Ge, Li Yi, Kaisheng Ma.
International Conference on Learning Representation (ICLR2023)
Non-Structured DNN Weight Pruning -- Is It Beneficial in Any Platform?
Xiaolong Ma, Sheng Lin, Shaokai Ye, Zhezhi He, Linfeng Zhang, Geng Yuan, Sia Huat, Tan, Zhengang Li, Deliang Fan, Xuehai Qian, Xue Lin, Kaisheng Ma, Yanzhi Wang
IEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS)
SMART: screen-based gesture recognition on commodity mobile devices
Zimo Liao, Zhicheng Luo, Qianyi Huang, Linfeng Zhang, Fan Wu, Qian Zhang, Yi Wang.
Annual International Conference on Mobile Computing and Networking (MobiCom21), Oral, 2018
*equal contribution
Wavelet J-Net: A Frequency Perceptive on Convolutional Neural Networks
Linfeng Zhang, Xiaoman Zhang, Chenglong Bao, Kaisheng Ma
International Joint Conference on Neural Networks (IJCNN2021)
CORSD: Class-Oriented Relational Self Distillation
Muzhou Yu, Sia Huat Tan, Kailu Wu, Runpei Dong, Linfeng Zhang, Kaisheng Ma
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP2023)
Preprints
Structured Knowledge Distillation Towards Efficient and Compact Multi-View 3D Detection
Linfeng Zhang, Yukang Shi, Hung-Shuo Tai, Zhipeng Zhang, Yuan He, Ke Wang, Kaisheng Ma
Region-aware knowledge distillation for efficient image-to-image translation
Linfeng Zhang, Xin Chen, Runpei Dong, Kaisheng Ma
Education

B.Eng. in SCIE, Northeastern University (in Shenyang, China)
Sep. 2015 - 2019

Ph.D. in Institute for Interdisciplinary Information Sciences, Tsinghua University
2019 - 2024 (expection)