I am an Applied Scientist at Amazon AWS AI Labs. I did my Ph.D. in Computer Science of University of North Carolina at Chapel Hill, working with Prof. Marc Niethammer and Prof. Colin Raffel. I am a member of the Royster Society of Fellows and was supported by its Dissertation Completion Fellowship. I have spent time at Google, Nvidia and Siemens Healthineers during my Ph.D. Before my Ph.D., I received my master’s degree on Imaging Science from Rochester Institute of Technology advised by Prof. Nathan Cahill on remote sensing image analysis and image registration. I received my bachelor’s degree from Department of Physics at Xi’an Jiaotong University, where I did research at Quantum Optics Lab with Prof. Pei Zhang.

My research focuses on improving data efficiency, robustness and generalization of deep neural networks, including topics like self/semi-supervised learning, vision and language learning, domain generalization and compositional generalization.

Selected Publications (Full List)

Benchmarking Zero-Shot Recognition with Vision-Language Models: Challenges on Granularity and Specificity
Zhenlin Xu, Yi Zhu, Tiffany Deng, Abhay Mittal, Yanbei Chen, Manchen Wang, Paolo Favaro, Joseph Tighe and Davide Modolo
Preprint

ScaleDet: A scalable multi-dataset object detector
Yanbei Chen, Manchen Wang, Abhay Mittal, Zhenlin Xu, Paolo Favaro, Joe Tighe, Davide Modolo
CVPR 2023

SimpleClick: Interactive image segmentation with simple vision transformers
Qin Liu, Zhenlin Xu, Gedas Bertasius, Marc Niethammer
ICCV 2023

Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Language
Zhenlin Xu, Marc Niethammer, and Colin Raffel.
NeurIPS 2022 (Oral)

Improving Dense Contrastive Learning with Dense Negative Pairs
Berk Iskender, Zhenlin Xu, Simon Kornblith, Enhung Chu, Maryam Khademi.
NeurIPS Workshop on Self-Supervised Learning - Theory and Practice 2022

iSegFormer: Interactive Segmentation via Transformers with Application to 3D Knee MR Images
Qin Liu, Zhenlin Xu, Yining Jiao, Marc Niethammer.
MICCAI 2022

Robust and Generalizable Visual Representation Learning via Random Convolutions
Zhenlin Xu, Deyi Liu, Junlin Yang, Colin Raffel, and Marc Niethammer.
ICLR 2021

Anatomical Data Augmentation via Fluid-based Image Registration
Zhengyang Shen, Zhenlin Xu, Sahin Olut, Marc Niethammer.
MICCAI 2020

Adversarial Data Augmentation via Deformation Statistics
Sahin Olut, Zhengyang Shen, Zhenlin Xu, Samuel Gerber, Marc Niethammer.
ECCV 2020

DeepAtlas: Joint Semi-Supervised Learning of Image Registration and Segmentation
Zhenlin Xu, Marc Niethammer.
MICCAI 2019 (Early Accepted)

Networks for Joint Affine and Non-parametric Image Registration
Zhengyang Shen, Xu Han, Zhenlin Xu, Marc Niethammer.
CVPR 2019

Academic Services

  • Conference Reviewer: NeurIPS, ICLR, ICML, AAAI, ICCV, CVPR, MICCAI
  • Journal Reviewer: MEDICAL IMAGE ANALYSIS (MEDIA), Transactions on Machine Learning Research(TMLR)

Misc

My Erdős number is 4 by coauthoring a paper with Dr. Nathan Cahill.