Shakeeb Murtaza
Postdoctoral Researcher · LIVIA

Shakeeb Murtaza

Postdoctoral Fellow, LIVIA, ÉTS Montréal
Researching weakly supervised localization

Pursuing reliable visual understanding from weak, scarce and noisy labels, from object localization to person re-identification and medical imaging.

0
Peer-reviewed papers
0
First-author papers
0
Top journal impact factor
0
Years of doctoral research
Weakly Supervised LocalizationPerson Re-IdentificationSelf-Supervised LearningVision TransformersDomain AdaptationTest-Time AdaptationPseudo-LabelingMedical ImagingMicroscopy Super-ResolutionHistologyCounterfactual ExplanationsClass Activation MappingVisual Attribution Weakly Supervised LocalizationPerson Re-IdentificationSelf-Supervised LearningVision TransformersDomain AdaptationTest-Time AdaptationPseudo-LabelingMedical ImagingMicroscopy Super-ResolutionHistologyCounterfactual ExplanationsClass Activation MappingVisual Attribution
About

Learning to see with fewer labels

Shakeeb Murtaza is a Postdoctoral Fellow at LIVIA, ÉTS Montréal, where he also completed his Ph.D. in 2025 on deep learning with minimal supervision for visual tasks. His research asks a deceptively hard question: how much visual understanding can a model reach when labels are scarce, weak, or noisy?

During his doctorate he focused on Weakly Supervised Object Localization (WSOL), localizing objects using only image-level labels. He contributed pseudo-labeling and self-supervised transformer methods (DiPS), class-activation co-localization for unconstrained videos (CoLo-CAM), text distillation (TeD-Loc), and a realistic evaluation protocol that exposed weaknesses in how WSOL is benchmarked.

His current work centers on Person Re-Identification, with interpretable, text-guided and part-based matching and test-time adaptation (InterPartAbility, DART3). He also works on medical and microscopy imaging, co-authoring the SR-CACO-2 super-resolution benchmark (NeurIPS 2024) and weakly-supervised histology adaptation, and on interpretable and explainable AI through counterfactual explanations, concept-controlled models and visual attribution.

He has authored 20+ peer-reviewed papers across venues including NeurIPS, WACV, CVPR workshops and the Pattern Recognition journal, and was named to the ÉTS Honour Roll in 2025.

Research interests

What Shakeeb works on

Weakly Supervised Object Localization

Localizing objects from only image-level labels, in images and unconstrained videos.

Person Re-Identification

Interpretable, text-guided and part-based matching, with test-time adaptation.

Learning with Minimal Supervision

Weak, self-supervised and pseudo-labeling strategies for visual recognition.

Vision Transformers & Self-Supervision

Transformer-based localization and discriminative proposal sampling.

Medical & Microscopy Imaging

Microscopy super-resolution (SR-CACO-2) and weakly-supervised histology adaptation.

Interpretable & Explainable AI

Counterfactual explanations, concept-controlled models and visual attribution.

Selected publications

Recent & representative work

WACV 2026 · under review

InterPartAbility: Text-Guided Part Matching for Interpretable Person Re-Identification

S. Murtaza, A. Shukla, R. Bhattacharya, M. Heritier, E. Granger
Pattern Recognition 2026 · under review

DART3: Leveraging Distance for Test-Time Adaptation in Person Re-Identification

R. Bhattacharya, S. Murtaza, A. Shukla, C. Desrosiers, J. Dolz, M. Heritier, E. Granger
Pattern Recognition 2026 · under review

TeD-Loc: Text Distillation for Weakly Supervised Object Localization

S. Murtaza, S. Belharbi, M. Pedersoli, E. Granger
Pattern Recognition 2025 · IF 7.5

CoLo-CAM: Class Activation Mapping for Object Co-Localization in Weakly-Labeled Unconstrained Videos

S. Belharbi, S. Murtaza, M. Pedersoli, I. Ben Ayed, L. McCaffrey, E. Granger
IEEE/CVF WACV 2025

A Realistic Protocol for Evaluation of Weakly Supervised Object Localization

S. Murtaza, S. Belharbi, M. Pedersoli, E. Granger
NeurIPS 2024 · Dataset

SR-CACO-2: A Dataset for Confocal Fluorescence Microscopy Image Super-Resolution

S. Belharbi, M. K. M. Whitford, P. Hoang, S. Murtaza, L. McCaffrey, E. Granger
IEEE/CVF CVPR Workshops 2024

Source-Free Domain Adaptation of Weakly-Supervised Object Localization Models for Histology

A. Guichemerre, S. Belharbi, T. Mayet, S. Murtaza, P. Shamsolmoali, L. McCaffrey, E. Granger
ANNPR 2024

Leveraging Transformers for Weakly Supervised Object Localization in Unconstrained Videos

S. Murtaza, M. Pedersoli, A. Sarraf, E. Granger
Image and Vision Computing 2023 · IF 4.2

DiPS: Discriminative Pseudo-Label Sampling with Self-Supervised Transformers for Weakly Supervised Object Localization

S. Murtaza, S. Belharbi, M. Pedersoli, A. Sarraf, E. Granger
Knowledge-Based Systems 2022 · IF 7.2

SoFTNet: A Concept-Controlled Deep Learning Architecture for Interpretable Image Classification

T. Zia, N. Bashir, M. A. Ullah, S. Murtaza

A full list of 20+ publications is available on Google Scholar.

Education

Academic background

  • Ph.D. in Engineering, ÉTS Montréal
    2020 to 2025 · Deep learning with minimal supervision for visual tasks · ÉTS Honour Roll 2025
  • Master's in Computer Science
    National Center of Artificial Intelligence, CUI, Pakistan · 2019 to 2020 · Medical-imaging research
Contact

Get in touch

🔗
🏢

Lab

LIVIA, 1100 Notre-Dame St W, Montréal, QC H3C 1K3