Behzad Bozorgtabar


Computer Vision Group Leader & Lecturer at EPFL
Senior Scientist at CHUV-EPFL


Behzad Bozorgtabar
email: behzad.bozorgtabar [at] epfl [dot] ch

ANNOUNCEMENT

I am currently looking for a PhD student with a focus on VLMs (Vision-Language Models). If you're interested, please reach out to me!


About Me


I'm a senior scientist and lecturer at the Signal Processing Lab (LTS5) at the École Polytechnique Fédérale de Lausanne (EPFL), with a joint affiliation with the Department of Radiology at the Lausanne University Hospital (CHUV) in Lausanne, Switzerland. At the EPFL-LTS5, I am the computer vision team leader for the medical imaging group. I am a member of European Lab for Learning & Intelligent Systems (ELLIS) and EPFL’s ELLIS Unit. Earlier, I was a Postdoctoral Researcher at IBM Research-Australia.

My principal research area lies at the intersection of computer vision and medical image analysis and machine learning. I specialize in self-supervised learning methods that minimize reliance on extensive labeling, advancing vision-based applications. My work also focuses on improving AI adaptability and generalization through techniques like test-time adaptation and domain generalization, crucial for reliable performance in real-world applications.



News


[Oct 2024] A paper has been accepted to WACV 2025.
[Oct 2024] I have received the IEEE TMI Distinguished Reviewer award.
[Sep 2024] I'll be serving as an Area Chair for CVPR 2025.
[July 2024] Our joint paper on Generalized Zero Shot Chest X-ray Classification has been accepted by Transactions on Medical Imaging (T-MI).
[July 2024] Our joint paper on active learning is now published in Medical Image Analysis (MedIA).
[July 2024] I have been appointed as an Associate Editor of IET Computer Vision.
[May 2024] I'll be serving as a reviewer for NeurIPS 2024.

EPFL Computer Vision Talks


EPFL CV Talks. I am organizing the EPFL Computer Vision Talks
YouTube Channel

Citations


citations. A complete list of my publications and patents can be found at Google Scholar

Recent Selected Publications


SimZSS *New* A Simple Framework For Open-Vocabulary Zero-Shot Segmentation
Thomas Stegmüller*, Tim Lebailly*, Nikola Dukic, Behzad Bozorgtabar, Tinne Tuytelaars, Jean-Philippe Thiran
arXiv 2024
arXiv

WACV25 *New* Self-Supervised Anomaly Segmentation via Diffusion Models with Dynamic Transformer UNet
Komal Kumar, Snehashis Chakraborty, Dwarikanath Mahapatra, Behzad Bozorgtabar, Sudipta Roy
WACV 2025
paper (coming soon) · github (cominng soon)

UnMix Un-Mixing Test-Time Normalization Statistics: Combatting Label Temporal Correlation
Devavrat Tomar*, Guillaume Vray*, Jean-Philippe Thiran, Behzad Bozorgtabar
ICLR 2024
project page · paper · github

CrIBo CrIBo: Self-Supervised Learning via Cross-Image Object-Level Bootstrapping
Tim Lebailly*, Thomas Stegmüller*, Behzad Bozorgtabar, Jean-Philippe Thiran, Tinne Tuytelaars
ICLR 2024 (Spotlight, Top 5%)
project page · paper · github

Distill_SODA Distill-SODA: Distilling Self-Supervised Vision Transformer for Source-Free Open-Set Domain Adaptation in Computational Pathology
Guillaume Vray*, Devavrat Tomar*, Jean-Philippe Thiran, Behzad Bozorgtabar
IEEE Transactions on Medical Imaging (T-MI) 2024
paper · github

Adasim Adaptive Similarity Bootstrapping for Self-Distillation based Representation Learning
Tim Lebailly*, Thomas Stegmüller*, Behzad Bozorgtabar, Jean-Philippe Thiran, Tinne Tuytelaars
ICCV 2023
paper · github

CrOC_main CrOC: Cross-View Online Clustering for Dense Visual Representation Learning
Thomas Stegmüller*, Tim Lebailly*, Behzad Bozorgtabar, Tinne Tuytelaars, Jean-Philippe Thiran
CVPR 2023
project page · paper · github

TeSLA_main TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentation
Devavrat Tomar, Guillaume Vray, Behzad Bozorgtabar, Jean-Philippe Thiran
CVPR 2023
project page · paper · github

AMAE AMAE: Adaptation of Pre-Trained Masked Autoencoder for Dual-Distribution Anomaly Detection in Chest X-Rays
Behzad Bozorgtabar, Dwarikanath Mahapatra, Jean-Philippe Thiran
MICCAI 2023
paper

ScoreNet ScoreNet: Learning Non-Uniform Attention and Augmentation for
Transformer-Based Histopathological Image Classification

Thomas Stegmüller, Behzad Bozorgtabar, Antoine Spahr, Jean-Philippe Thiran
WACV 2023
project page · paper · github

ANOM Anomaly Detection and Localization Using Attention-Guided Synthetic Anomaly
and Test-Time Adaptation

Behzad Bozorgtabar, Dwarikanath Mahapatra, Jean-Philippe Thiran
BMVC 2022
paper

OptTTA OptTTA: Learnable Test-Time Augmentation for
Source-Free Medical Image Segmentation Under Domain Shift

Devavrat Tomar, Guillaume Vray, Jean-Philippe Thiran, Behzad Bozorgtabar
MIDL 2022 (Oral)
project page · paper · github

SRMA. Self-Rule to Multi-Adapt: Generalized Multi-source Feature Learning
Using Unsupervised Domain Adaptation for Colorectal Cancer Tissue Detection

Christian Abbet, Linda Studer, Andreas Fischer, Heather Dawson, Inti Zlobec,
Behzad Bozorgtabar, Jean-Philippe Thiran
MedIA Journal 2022
paper · github

SST. Self-Supervised Generative Style Transfer for One-Shot Medical Image Segmentation
Devavrat Tomar, Behzad Bozorgtabar, Manana Lortkipanidze, Guillaume Vray,
Mohammad Saeed Rad, Jean-Philippe Thiran
WACV 2022
paper · github

SegGini. Learning Whole-Slide Segmentation from Inexact and
Incomplete Labels using Tissue Graphs

Valentin Anklin, Pushpak Pati, Guillaume Jaume, Behzad Bozorgtabar,
Antonio Foncubierta-Rodríguez, Jean-Philippe Thiran, Mathilde Sibony,
Maria Gabrani, Orcun Goksel
MICCAI 2021
paper · github

SOoD. SOoD: Self-Supervised Out-of-Distribution Detection
Under Domain Shift for Multi-Class Colorectal Cancer Tissue Types

Behzad Bozorgtabar, Guillaume Vray, Dwarikanath Mahapatra, Jean-Philippe Thiran
ICCVW 2021
paper · github

CVPR2021. Quantifying Explainers of Graph Neural Networks in Computational Pathology
Guillaume Jaume, Pushpak Pati, Behzad Bozorgtabar, Antonio Foncubierta-Rodríguez,
Florinda Feroce, Anna Maria Anniciello, Tilman Rau, Maria Gabrani,
Jean-Philippe Thiran, Orcun Goksel
CVPR 2021
paper · github

T-MI. Self-Attentive Spatial Adaptive Normalization for Cross-Modality Domain Adaptation
Devavrat Tomar, Manana Lortkipanidze, Guillaume Vray,
Behzad Bozorgtabar, Jean-Philippe Thiran
IEEE Transactions on Medical Imaging (T-MI) 2021
paper · github

MIDL2021. Self-Rule to Adapt: Learning Generalized Features from Sparsely-Labeled Data
Using Unsupervised Domain Adaptation for Colorectal Cancer Tissue Phenotyping

Christian Abbet, Linda Studer, Andreas Fischer, Heather Dawson, Inti Zlobec,
Behzad Bozorgtabar, Jean-Philippe Thiran
MIDL 2021
paper · github

ISBI2021. Self-Taught Semi-Supervised Anomaly Detection on Upper Limb X-rays
Antoine Spahr , Behzad Bozorgtabar, Jean-Philippe Thiran
ISBI 2021
paper· github

ISBI2021. Benefiting from Bicubically Down-Sampled Images for
Learning Real-World Image Super-Resolution

Mohammad Saeed Rad, Thomas Yu, Claudiu Musat, Hazım Kemal Ekenel,
Behzad Bozorgtabar, Jean-Philippe Thiran
WACV 2021
paper

SALAD. SALAD: Self-Supervised Aggregation Learning for Anomaly Detection on X-Rays
Behzad Bozorgtabar, Dwarikanath Mahapatra, Guillaume Vray, Jean-Philippe Thiran
MICCAI 2020
paper · github

Self-Rule. Divide-and-Rule: Self- Supervised Learning for Survival Analysis in Colorectal Cancer
Christian Abbet, Inti Zlobec, Behzad Bozorgtabar, Jean-Philippe Thiran
MICCAI 2020
paper · github

CVPR2020. Pathological Retinal Region Segmentation From OCT Images
Using Geometric Relation Based Augmentation

Dwarikanath Mahapatra, Behzad Bozorgtabar, Jean-Philippe Thiran, Ling Shao
CVPR 2020
paper

Syndemo. SynDeMo: Synergistic Deep Feature Alignment for Joint Learning of Depth and Ego-Motion
Behzad Bozorgtabar, Mohammad Saeed Rad, Dwarikanath Mahapatra, Jean-Philippe Thiran
ICCV 2019
paper · supplementary material

SROBB. SROBB: Targeted Perceptual Loss for Single Image Super-Resolution
Mohammad Saeed Rad, Behzad Bozorgtabar, Urs-Viktor Marti,
Max Basler, Hazım Kemal Ekenel,
Jean-Philippe Thiran
ICCV 2019
paper · supplementary material

FG2019. Using Photorealistic Face Synthesis and Domain Adaptation
to Improve Facial Expression Analysis

Behzad Bozorgtabar, Mohammad Saeed Rad, Hazım Kemal Ekenel, Jean-Philippe Thiran
FG 2019
paper · github

CVIU2019. Learn to Synthesize and Synthesize to Learn
Behzad Bozorgtabar, Mohammad Saeed Rad, Hazım Kemal Ekenel, Jean-Philippe Thiran
CVIU 2019
paper · github

NeurIPS18. Image-Level Attentional Context Modeling Using Nested-Graph Neural Networks
Guillaume Jaume, Behzad Bozorgtabar, Hazım Kemal Ekenel,
Jean-Philippe Thiran, Maria Gabrani
NeurIPS 2018
paper

MSMCT. MSMCT: Multi-State Multi-Camera Tracker
Behzad Bozorgtabar, Roland Goecke
IEEE TCSVT 2018
paper

Grants


Personalized Health and Related Technologies (PHRT)
Swiss Cancer League
Discovery Translation Fund (DTF 2.0)

PhD Students


Thomas Stegmüller
Guillaume Vray
Devavrat Tomar

Current Teaching


2019-PresentImage analysis and pattern recognition (EE-451-4 ECTS- Bozorgtabar & Thiran), EPFL
2019-PresentLab in signal and image processing (EE-490(f)-4 ECTS- Bozorgtabar & Thiran), EPFL


© Template from William Peebles. Behzad Bozorgtabar | Last updated: November 4 2024