Behzad Bozorgtabar

Associate Professor, Aarhus University

Lecturer, Swiss Federal Institute of Technology Lausanne

Associate Professor, University of Southern Denmark - SDU

Joined

April 2018

Names

Behzad Bozorgtabar

Emails

****@epfl.ch (Confirmed)

****@gmail.com (Confirmed)

****@imada.sdu.dk (Confirmed)

****@ece.au.dk (Confirmed)

Personal Links

Career & Education History

Associate Professor

Aarhus University (ece.au.dk)

2026 – Present

Lecturer

Swiss Federal Institute of Technology Lausanne (epfl.ch)

2017 – Present

Associate Professor

University of Southern Denmark - SDU (sdu.dk)

2025 – 2026

Postdoc

International Business Machines (ibm.com)

2016 – 2017

Advisors, Relations & Conflicts

Social

Julio Silva-Rodríguez

Present

Social

Jose Dolz

Present

Social

Huazhu Fu

Present

Coworker

Benoit Albert Bernard Dufumier

2023 – Present

Social

Sotirios Tsaftaris

2023 – Present

Social

Faisal mahmood

2022 – Present

Coworker

Meritxell Bach Cuadra

2020 – Present

Expertise

Agentic AI

2025 – Present

Vision-Language Models

2024 – Present

Test-Time Adaptation

2020 – Present

Self-Supervised Learning

2017 – Present

Deep Learning

2016 – Present

Publications

The 3rd Workshop on Test-Time Updates (TTU)
Evan Shelhamer, Francesco Croce, Teresa Yeo, Shuaicheng Niu, Behzad Bozorgtabar, Xiaoxiao Li
- ICLR 2026 Workshop Proposals
- Readers: Everyone
ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains
Guillaume Vray, Devavrat Tomar, Xufeng Gao, Jean-Philippe Thiran, Evan Shelhamer, Behzad Bozorgtabar
- NeurIPS 2025 poster
- Readers: Everyone
UniViT: Unifying Image and Video Understanding in One Vision Encoder
Feilong Tang, Xiang An, Haolin Yang, Yin Xie, Kaicheng Yang, Ming Hu, Zheng Cheng, Xingyu Zhou, Zimin Ran, Imran Razzak, Ziyong Feng, Behzad Bozorgtabar, Jiankang Deng, Zongyuan Ge
- NeurIPS 2025 poster
- Readers: Everyone
A Simple Framework for Open-Vocabulary Zero-Shot Segmentation
Thomas Stegmüller, Tim Lebailly, Nikola Đukić, Behzad Bozorgtabar, Tinne Tuytelaars, Jean-Philippe Thiran
- ICLR 2025 Poster
- Readers: Everyone
Distill-SODA: Distilling Self-Supervised Vision Transformer for Source-Free Open-Set Domain Adaptation in Computational Pathology
Guillaume Vray, Devavrat Tomar, Behzad Bozorgtabar, Jean-Philippe Thiran
- IEEE Trans. Medical Imaging 2024
- Readers: Everyone
Self-supervised learning-based cervical cytology for the triage of HPV-positive women in resource-limited settings and low-data regime
Thomas Stegmüller, Christian Abbet, Behzad Bozorgtabar, Holly Clarke, Patrick Petignat, Pierre Vassilakos, Jean-Philippe Thiran
- Comput. Biol. Medicine 2024
- Readers: Everyone
ALFREDO: Active Learning with FeatuRe disEntangelement and DOmain adaptation for medical image classification
Dwarikanath Mahapatra, Ruwan B. Tennakoon, Yasmeen George, Sudipta Roy, Behzad Bozorgtabar, Zongyuan Ge, Mauricio Reyes
- Medical Image Anal. 2024
- Readers: Everyone
Combining Graph Transformers Based Multi-Label Active Learning and Informative Data Augmentation for Chest Xray Classification
Dwarikanath Mahapatra, Behzad Bozorgtabar, Zongyuan Ge, Mauricio Reyes, Jean-Philippe Thiran
- AAAI 2024
- Readers: Everyone
Un-Mixing Test-Time Normalization Statistics: Combatting Label Temporal Correlation
Devavrat Tomar, Guillaume Vray, Jean-Philippe Thiran, Behzad Bozorgtabar
- ICLR 2024
- Readers: Everyone
GANDALF: Graph-based transformer and Data Augmentation Active Learning Framework with interpretable features for multi-label chest Xray classification
Dwarikanath Mahapatra, Behzad Bozorgtabar, Zongyuan Ge, Mauricio Reyes
- Medical Image Anal. 2024
- Readers: Everyone

View all 108 publications

Co-Authors

View all 137 co-authors