Ziyu Jiang (蒋子宇)

Ziyu Jiang (蒋子宇)

About Me

I am a researcher at NEC America Lab. Previously, I was a Ph.D. student at Texas A&M University supervised by Prof. Zhangyang Wang. My research interests lie in Self-Supervised (SS) Learning, Efficient Training, Indoor Scene Occlusion Reasoning, etc. His works are published at various top conferences such as NeurIPS, ICML, ICLR, CVPR, and ECCV.

Selected Publications

Layer Grafted Pre-training: Bridging Contrastive Learning And Masked Image Modeling For Better Representations
Ziyu Jiang, Yinpeng Chen, Mengchen Liu, Dongdong Chen, Xiyang Dai, Lu Yuan, Zicheng Liu, Zhangyang Wang
[Paper] [Code]
Back Razor: Memory-Efficient Transfer Learning by Self-Sparsified Backpropogation
Ziyu Jiang*, Xuxi Chen*, Xueqin Huang, Xianzhi Du, Denny Zhou, Zhangyang Wang
[Paper] [Code]
M3ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design
Hanxue Liang*, Zhiwen Fan*, Rishov Sarkar, Ziyu Jiang, Tianlong Chen, Kai Zou, Yu Cheng, Cong Hao, and Zhangyang Wang
[Paper] [Code]
DnA: Improving Few-shot Transfer Learning with Low-Rank Decomposition and Alignment
Ziyu Jiang, Tianlong Chen, Xuxi Chen, Yu Cheng, Luowei Zhou, Lu Yuan, Ahmed Awadallah, Zhangyang Wang
[Paper] [Code]
Improving Contrastive Learning onImbalanced Data via Open-World Sampling
Ziyu Jiang, Tianlong Chen, Ting Chen, Zhangyang Wang
[Paper] [Code]
Self-Damaging Contrastive Learning
Ziyu Jiang, Tianlong Chen, Bobak Mortazavi, Zhangyang Wang
[Paper] [Code]
Robust Pre-Training by Adversarial Contrastive Learning
Ziyu Jiang, Tianlong Chen, Ting Chen, Zhangyang Wang
[Paper] [Code]
Peek-a-Boo: Occlusion Reasoning in Indoor Scenes With Plane Representations
Ziyu Jiang, Buyu Liu, Samuel Schulter, Zhangyang Wang, Manmohan Chandraker
[Paper] [Project Page]
E2-Train: Training State-of-the-art CNNs with Over 80% Less Energy
Yue Wang*, Ziyu Jiang*, Xiaohan Chen*, Pengfei Xu, Yang Zhao, Yingyan Lin, Zhangyang Wang
[Paper] [Code]
Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images
Wuyang Chen*, Ziyu Jiang*, Zhangyang Wang, Kexin Cui, Xiaoning Qian
[Paper] [Code]

Professional Experience

May - August, 2022
Research Intern, Microsoft, Redmond, WA

Mentors: Yinpeng Chen
Research on self-supervised pre-training

  • Explore self-supervised methods that can combine the benefits of both Mask Image Modeling (MIM) and Contrastive Learning (CL).
May - August, 2021
Research Intern, Microsoft, Redmond, WA

Mentors: Luowei Zhou, Yu Cheng
Research on self-supervised transfer learning

  • Explore self-supervised methods with better few-shot performance via improving both pre-training and fine-tuning.
June - November, 2020
Research Intern, Bytedance AI Lab, Mountain View, CA

Mentors: Linjie Yang
Research on video segmentation

  • Explore efficient approach for video segmentation.
June - August, 2019
Research Intern, NEC laboratories america inc, San. Jose, CA

Mentors: Buyu, Liu
Research on indoor scene understanding

  • Explore better algorithms for semantic segmenation of indoor scene.