Ze Wang
Contact: ze.wang.0610 [at] gmail.com
I am currently a Research Scientist at Luma AI.
Previously, I was an Applied Research Scientist at AMD, working on open-source research at the GenAI team. Before that, I was a Postdoctoral Research Associate at Purdue University, working with Prof. Qiang Qiu.
I received my Ph.D. in Electrical and Computer Engineering from Purdue University in 2023, advised by Prof. Qiang Qiu and Prof. Guillermo Sapiro. Before joining Purdue, I was a Ph.D. student at Duke University. I got my B.E. from Beihang University in 2017.
My research focuses on computer vision models that efficiently learn and adapt with minimal supervision, including vision model adaptation, few-shot learning, and generative models.
Recent Publications
- 2023
Energy-Inspired Self-Supervised Pretraining for Vision Models
Ze Wang, Jiang Wang, Zicheng Liu, Qiang Qiu
ICLR Notable-top-25%, 2023
[pdf]
Meta-OLE: Meta-learned Orthogonal Low-Rank Embedding
Ze Wang, Yue Lu, Qiang Qiu
WACV, 2023
[pdf]
- 2022
Few-Shot Fast-Adaptive Anomaly Detection
Ze Wang, Yipin Zhou, Rui Wang, Tsung-Yu Lin, Ashish Shah, Ser-Nam Lim
NeurIPS, 2022
Energy-Inspired Self-Supervised Pretraining for Vision Models
Ze Wang, Jiang Wang, Zicheng Liu, Qiang Qiu
ICML Pre-training Workshop, 2022
[pdf]
Continual Learning with Filter Atom Swapping
Zichen Miao, Ze Wang, Wei Chen, Qiang Qi
ICLR Spotlight, 2022
[pdf]
- 2021
Image Generation using Continuous Filter Atoms
Ze Wang, Seunghyun Hwang, Zichen Miao, Qiang Qiu
NeurIPS Spotlight, 2021
[pdf]
Learning to Learn Dense Gaussian Processes for Few-Shot Learning
Ze Wang, Zichen Miao, Xiantong Zhen, Qiang Qiu
NeurIPS, 2021
[pdf]
Spatiotemporal Joint Filter Decomposition in 3D Convolutional Neural Networks
Zichen Miao, Ze Wang, Xiantong Zhen, Qiang Qiu
NeurIPS, 2021
[pdf]
Adaptive Convolutions with Per-pixel Dynamic Filter Atom
Ze Wang, Zichen Miao, Jun Hu, Qiang Qiu
ICCV, 2021
[pdf] [code]
Cirrus: A Long-range Bi-pattern LiDAR Dataset
Ze Wang, Sihao Ding, Ying Li, Jonas Fenn, Sohini Roychowdhury, Andreas Wallin, Lane Martin, Scott Ryvola, Guillermo Sapiro, Qiang Qiu
ICRA, 2021
[pdf] [dataset]
Using Text to Teach Image Retrieval
Haoyu Dong, Ze Wang, Qiang Qiu, Guillermo Sapiro
CVPR Multimodal Learning and Applications Workshop, 2021
[pdf]
- 2020
A Dictionary Approach to Domain-Invariant Learning in Deep Networks
Ze Wang, Xiuyuan Cheng, Guillermo Sapiro, Qiang Qiu
NeurIPS, 2020
[pdf]
Stochastic Conditional Generative Networks with Basis Decomposition
Ze Wang, Xiuyuan Cheng, Guillermo Sapiro, Qiang Qiu
ICLR, 2020
[pdf]
- 2019
Range Adaptation for 3D Object Detection in LiDAR
Ze Wang, Ding, Ying Li, Minming Zhao, Sohini Roychowdhury, Andreas Wallin, Guillermo Sapiro, Qiang Qiu
ICCV Workshop on Autonomous Driving Best Paper Award, 2019
[pdf]
The structure transfer machine theory and applications
Baochang Zhang, Wankou Yang, Ze Wang, Lian Zhuo, Jungong Han, Xiantong Zhen
IEEE Transactions on Image Processing, 2019
[pdf]
Understanding Urban Dynamics via Context-aware Tensor Factorization with Neighboring Regularization
Jingyuan Wang, Junjie Wu, Ze Wang, Fei Gao, Zhang Xiong
IEEE Transactions on Knowledge and Data Engineering, 2019
[pdf]
For earier publications please refer to my Google Scholar.