I am a postdoctoral researcher in the Department of Computer Science and Technology, Tsinghua University, collaborating with Prof. Jun Zhu. Before that, I obtained my Ph. D. degree from the School of Computer Science and Technology, University of Chinese Academy of Sciences in July, 2024 advised by Prof. Yingjie Tian.

My research focuses on developing efficient deep learning algorithms under limited resources. My current interests include Data-Centric AI, AIGC and Visual Understanding.

News

• 2024/08 We won the 3rd place in the 1st DD challenge @ ECCV 2024
• 2024/06 I obtained my Ph. D. degree after four years of diligent work.
• 2024/02 One paper accepted in CVPR 2024.

Publications

2024

• Generative Dataset Distillation Based on Diffusion Model
  Duo Su, Junjie Hou, Guang Li, Ren Togo, Rui Song, Takahiro Ogawa, Miki Haseyama
  European Conference on Computer Vision Workshop (ECCV), Milano, Italy, 2024

• D⁴M: Dataset Distillation via Disentangled Diffusion Model
  Duo Su, Junjie Hou, Weizhi Gao, Yingjie Tian, Bowen Tang
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, USA, 2024

• Unified Image Harmonization with Region Augmented Attention Normalization
  Junjie Hou, Yuqi Zhang, Duo Su
  Annals of Data Science, 2022

• Adaptive Robust Loss for Landmark Detection
  Yingjie Tian, Duo Su, Shilin Li
  Information Fusion, 2024

2023

• Linear-Exponential Loss Incorporated Deep Learning for Imbalanced Classification
  Saiji Fu, Duo Su, Shilin Li, Shiding Sun, Yingjie Tian
  ISA Transactions, 2023

2022

• Recent advances on loss functions in deep learning for computer vision
  Yingjie Tian, Duo Su, Stanislao Lauria, Xiaohui Liu
  Neurocomputing, 2022

Services

Invited Speaker

• 2023/12 I was invited to give an academic report on the ‘ShuYunGuangZhi’ Academic Innovation Forum at the Department of Mathematics in Science College, CAU.

Reviewer

Journal: TPAMI, TNNLS, TMLR, TCSVT, KBS, Neurocomputing
Conference: AAAI, IJCAI

Competitions

• Our team (Guang Li, Duo Su, Junjie Hou, Ren Togo, Rui Song, Takahiro Ogawa, Miki Haseyama) won the third place in The First Dataset Distillation Challenge @ ECCV 2024 Workshop.

Honors and Awards

• Beijing Outstanding Graduate Award, 2020.06
• Beijing Outstanding Graduate Award, 2017.06