About Me
Hello, I am Tushar Kataria, a PhD candidate at University of Utah, Utah in School of Computing. I am in Scientific Computing and Imaging Institute advised by Prof. Shireen Elhabian.
Research Interests
Broader research interests are image processing, medical image processing, deep learning and computer vision. Specifically, I am interested in Semantic Segmentation, Instance Segmentation and Domain Adaptation problems for medical imaging datasets. I am also interested in Statistical Shape Modelling and MultiModal machine learning.
Advisor: Prof. Shireen Elhabian
Collaborators: Prof. Beatrice S. Knudsen, Shikha Dubey, Mokshagna Sai Teja Karanam, Krithika Iyer, Vivek Gupta, Jadie Adams, Rachaell Nihalaani, Janmesh Ukey, Abu Zahid Bin Aziz
Reviewer Services: MICCAI 2024, ARR June Cycle 2024
Recent News
[Nov 2024, EMNLP 2025] Evaluating Concurrent Robustness of Language Models Across Diverse Challenge Sets
Author List: Vatsal Gupta, Pranshu Pandya,Tushar Kataria, Vivek Gupta, Dan Roth
[Oct 2024, Accepted to WACV-2025] EfficientMorph: Parameter-Efficient Transformer-Based Architecture for 3D Image Registration
Author List: Abu Zahid Bin Aziz, Mokshagna Sai Teja Karanam,Tushar Kataria,Shireen Elhabian.
[Aug 2024 -May 2024] Summer Internship at Johnson and Johnson Innovation Labs. During my internship as a Digital Pathology Imaging Intern, I focused on developing methods for TILs detection and contributed to various image processing projects.
[Mar 2024, Accepted In ShapeMI, MICCAI 2024] MASSM: An End-to-End Deep Learning Framework for Multi-Anatomy Statistical Shape Modeling Directly From Images
Author List: Janmesh Ukey, Tushar Kataria, Shireen Y. Elhabian
[Mar 2024, Accepted In MICCAI 2024] Estimation and Analysis of Slice Propagation Uncertainty in 3D Anatomy Segmentation
Author List: Rachaell Nihalaani, Tushar Kataria, Jadie Adams, Shireen Y. Elhabian
[Feb 2024, ISBI 2024] Unsupervised Domain Adaptation for Medical Image Segmentation via Feature-space Density Matching.
Author List: Tushar Kataria, Beatrice Knudsen, Shireen Elhabian.
Archived Papers
[July 2024, Archive Version] Weakly SSM : On the Viability of Weakly Supervised Segmentations for Statistical Shape Modeling
Author List: Janmesh Ukey, Tushar Kataria, Shireen Y. Elhabian
[July 2024, Archive Version] NTSEBENCH: Cognitive Reasoning Benchmark for Vision Language Models
Author List: Pranshu Pandya, Agney S Talwarr, Vatsal Gupta, Tushar Kataria, Vivek Gupta, Dan Roth
[Mar 2024, Archive Version] StainDiffuser: MultiTask Dual Diffusion Model for Virtual Staining
Author List: Tushar Kataria, Beatrice Knudsen, Shireen Elhabian.
Equal Contribution