About Me
I am currently a postdoctoral researcher in the Dept. of Computer Science and Engineering in Ohio State University. I'm fortunate to work with Wei-Lun Chao, Yu Su and Tanya Berger-Wolf. I obtained my Ph.D. in 2024 from College of Control Science and Engineering, Zhejiang University, Hangzhou, China. I was supervised by Prof. Wei Jiang. Previously, I received my B.Eng. in Zhejiang University in 2019. During Sep. 2022 - Oct. 2023, I was a visiting scholar at HPC AI Lab, National University of Singapore, under the supervision of Prof. Yang You.
Research Interest
- Imageomics
- Data-centric Efficient Training
- Computer Vision
Selected Publications
A full publication list is available in my google scholar page.
(* denotes equal contribution)
[arXiv] Group Distributionally Robust Dataset Distillation with Risk Minimization [PDF] [Code]
Saeed Vahidian*, Mingyu Wang*, Jianyang Gu*, Vyacheslav Kungurtsev, Wei Jiang and Yiran Chen.
- Robust Dataset Distillation combines clustering with the minimization of a risk measure on the loss.
- Robust Dataset Distillation substantially enhances the robustness across domain-shifted testing sets.
[CVPR 2024] Efficient Dataset Distillation via Minimax Diffusion [PDF] [Code]
Jianyang Gu, Saeed Vahidian, Vyacheslav Kungurtsev, Haonan Wang, Wei Jiang, Yang You and Yiran Chen.
- Minimax Diffusion only requires 1 hour to finish the distillation for a 10-class subset of full-sized ImageNet.
- Minimax Diffusion generates representative and diverse images, yielding state-of-the-art validation performance.
[AAAI 2024] Summarizing Stream Data for Memory-Restricted Online Continual Learning [PDF] [Code]
Jianyang Gu, Kai Wang, Wei Jiang, and Yang You.
- SSD summarizes the informtion flow in online continual learning into informative samples.
- SSD significantly improves the replay effects, especially for circumstances with restricted memory.
[ICCV 2023] Dataset Quantization [PDF] [Code]
Daquan Zhou*, Kai Wang*, Jianyang Gu*, Dongze Lian, Xiangyu Peng, Yifan Zhang, Yang You, and Jiashi Feng.
- DQ targets at compressing large-scale datasets into subsets with lossless validation performance.
- DQ only requires 60% ImageNet and 20% Alpaca's instruction tuning data to achieve lossless training.
[ICCV 2023] DREAM: Efficient Dataset Distillation by Representative Matching [PDF] [Code]
Yanqing Liu*, Jianyang Gu*, Kai Wang, Zheng Zhu, Wei Jiang, and Yang You.
- DREAM aims to improve the training efficiency by only calculating matching metrics with representative samples.
- DREAM only requires less than 20% of original iterations to achieve baseline performance.
[arXiv] DiM: Distilling Dataset into Generative Model [PDF] [Code]
Kai Wang*, Jianyang Gu*, Daquan Zhou, Zheng Zhu, Wei Jiang, and Yang You.
- DiM opens up a new generative scheme for dataset distillation by condensing the information into models.
- DiM generates diverse images on the fly, providing outstanding distillation performance with small extra training consumption.
-
[ICLR 2024] InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning. [PDF] [Code]
Ziheng Qin*, Kai Wang*, Zangwei Zheng, Jianyang Gu, Xiangyu Peng, Zhaopan Xu, Daquan Zhou, Lei Shang, Baigui Sun, Xuansong Xie, Yang You
[arXiv] Color Prompting for Data-Free Continual Unsupervised Domain Adaptive Person Re-Identification [PDF] [Code]
Jianyang Gu, Hao Luo, Kai Wang, Wei Jiang, Yang You, and Jian Zhao.
- CoP learns the color distribution conditioned on the tasks and image contents during the continual learning process.
- CoP provides substantial improvements on anti-forgetting and generalization without storing images of previous tasks.
[CVPR 2023] MSINet: Twins Contrastive Search of Multi-Scale Interaction for Object ReID [PDF] [Code]
Jianyang Gu, Kai Wang, Hao Luo, Chen Chen, Wei Jiang, Yuqiang Fang, Shanghang Zhang, Yang You, and Jian Zhao.
- MSINet searches the optimal interation between multi-scale branches with a twins contrastive mechanism.
- MSINet yeilds better performance on both supervised and unsupervised tasks with limited parameter size.
[IEEE TIFS] Multi-View Evolutionary Training for Unsupervised Domain Adaptive Person Re-Identification [PDF]
Jianyang Gu, Weihua Chen, Hao Luo, Fan Wang, Hao Li, Wei Jiang, and Weijie Mao.
- MET effectively reduces the clustering noise from the dimensions of snapshot quality and temporal consistency.
- MET significantly improves the training robustness by high-quality clustering results, leading to better model performance.
-
[IEEE TITS] Transformer-Based Domain-Specific Representation for Unsupervised Domain Adaptive Vehicle Re-Identification. [PDF]
Ran Wei, Jianyang Gu, Shuting He, and Wei Jiang
-
[Pattern Anal Applic] An efficient global representation constrained by Angular Triplet loss for vehicle re-identification. [PDF]
Jianyang Gu, Wei Jiang, Hao Luo, and Hongyan Yu.
-
[ECCVW 2020] 1st Place Solution to VisDA-2020: Bias Elimination for Domain Adaptive Pedestrian Re-identification. [PDF] [Code]
Jianyang Gu, Hao Luo, Weihua Chen, Yiqi Jiang, Yuqi Zhang, Shuting He, Fan Wang, Hao Li, and Wei Jiang.
Experience
-
OPPO Research Intern
Nov. 2021 - Jun. 2022. Focused on domain generalizable person re-identification and video action recognition.
-
Alibaba Research Intern
Jun. 2020 - Apr. 2021. Focused on unsupervised domain adaptive person re-identification. Awarded as the annual outstanding research intern in 2020.
-
Yitu Tech. CI Intern
May. 2018 - Sept. 2018. Helped build up the continuous integration pipeline of products.
Competitions & Awards
-
ActivityNet Temporal Action Localization Challenge
Third Place. CVPR Workshop 2022.
-
SoccerNet Challenge
Third Place. CVPR Workshop 2022.
-
AICity Challenge
First Place. CVPR Workshop 2021.
-
National AI Challenge
Second Prize. 2020.
-
Visual Domain Adaptation Challenge
First Place. ECCV Workshop 2020.
-
Robocup Montreal
First Place. 2018.
Academic Service
-
Conference Reviewer: CVPR, ICCV, ECCV, NeurIPS, ACMMM, ACCV
-
Journal Reviewer: IEEE TPAMI, PR, CVIU, IEEE TCSVT
Other Information
-
President, Student AI Association of Zhejiang University, Aug. 2020 - Jun. 2021
-
Part of my photography works.
Contact Me
You are welcome to contact me via Email or WeChat (ID: ypneverland)