Scholar
Zhenlin Xu
Google Scholar ID: RPGduXAAAAAJ
Boson AI
Citations & Impact
Citations
1,227
H-index
14
i10-index
15
Publications
20
Co-authors
3
list available
Publications
Resume (English only)
Academic Achievements
- Benchmarking Zero-Shot Recognition with Vision-Language Models: Challenges on Granularity and Specificity, Preprint
- ScaleDet: A scalable multi-dataset object detector, CVPR 2023
- SimpleClick: Interactive image segmentation with simple vision transformers, ICCV 2023
- Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Language, NeurIPS 2022 (Oral)
- Improving Dense Contrastive Learning with Dense Negative Pairs, NeurIPS Workshop on Self-Supervised Learning - Theory and Practice 2022
- iSegFormer: Interactive Segmentation via Transformers with Application to 3D Knee MR Images, MICCAI 2022
- Robust and Generalizable Visual Representation Learning via Random Convolutions, ICLR 2021
- Anatomical Data Augmentation via Fluid-based Image Registration, MICCAI 2020
- Adversarial Data Augmentation via Deformation Statistics, ECCV 2020
- DeepAtlas: Joint Semi-Supervised Learning of Image Registration and Segmentation, MICCAI 2019 (Early Accepted)
- Networks for Joint Affine and Non-parametric Image Registration, CVPR 2019
Background
- Research interests: Improving data efficiency, robustness, and generalization of deep neural networks, including self/semi-supervised learning, vision and language learning, domain generalization, and compositional generalization.
Miscellany
- My Erdős number is 4 by coauthoring a paper with Dr. Nathan Cahill.
