Fardad Dadboud

Room 5004, SITE Building

800 King Edward

Ottawa, Ontario, Canada, K1N 6N5

Currently, I am a Ph.D. candidate at the University of Ottawa’s School of Electrical Engineering and Computer Science (SEECS). In addition to my academic pursuits, I volunteer as a Visitor at Canada’s National Research Council (NRC). My research is supervised by Professor Miodrag Bolic at the University of Ottawa.

My research interests lie at the intersection of computer vision, deep learning, and machine learning, with a specific focus on autonomous vehicles. Currently, I’m deeply engaged in addressing challenges related to domain shift, out-of-distribution detection, and unsupervised or test-time domain adaptation.

I hold a Master of Science in Biomedical Engineering from Sharif University of Technology and a Bachelor of Science in Electrical Engineering from Babol Noshirvani University of Technology.

[Curriculum Vitae]

Current Interests

Meta-Learning
Out-of-Distribution (OOD) Detection
Test-Time Adaptation
Unsupervised Domain Adaptation/Generalization
Video Understanding
Object Detection and Tracking
Uncertainty Evaluation
Resilient AI

I am passionate about bringing cutting-edge research into real-world applications and am actively seeking opportunities in both corporate and freelance roles to apply my skills and knowledge.

news

Feb 01, 2025	I have joined Neptune Technologies as s Senior Machine Learning Engineer (Intern).
Oct 28, 2024	Our paper “DrIFT: Autonomous Drone Dataset with Integrated Real and Synthetic Data, Flexible Views, and Transformed Domains” was accepted at IEEE/CVF WACV 2025.
Dec 07, 2021	I am invited by UOttawa for the ceremony of excellence in the faculty of Engineering. See photos here and video here.
Sep 21, 2021	CARG-UOTTAWA group won the second place of Drone-vs-Bird Detection Challenge in conjunction with the 4th WOSDETC of IEEE AVSS 2021.

selected publications

WACV
DrIFT: Autonomous Drone Dataset with Integrated Real and Synthetic Data, Flexible Views, and Transformed Domains

Fardad Dadboud, Hamid Azad, Varun Mehta, Miodrag Bolic, and Iraj Mantegh

2025

Abs Bib HTML PDF

Dependable visual drone detection is crucial for the secure integration of drones into the airspace. However, drone detection accuracy is significantly affected by domain shifts due to environmental changes, varied points of view, and background shifts. To address these challenges, we present the DrIFT dataset, specifically developed for visual drone detection under domain shifts. DrIFT includes fourteen distinct domains, each characterized by shifts in point of view, synthetic-to-real data, season, and adverse weather. DrIFT uniquely emphasizes background shift by providing background segmentation maps to enable background-wise metrics and evaluation. Our new uncertainty estimation metric, MCDO-map, features lower postprocessing complexity, surpassing traditional methods. We use the MCDO-map in our uncertainty-aware unsupervised domain adaptation method, demonstrating superior performance to SOTA unsupervised domain adaptation techniques.
@article{dadboud2025DrIFT, title = {DrIFT: Autonomous Drone Dataset with Integrated Real and Synthetic Data, Flexible Views, and Transformed Domains}, author = {Dadboud, Fardad and Azad, Hamid and Mehta, Varun and Bolic, Miodrag and Mantegh, Iraj}, booktitle = {2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) }, pages = {1--8}, year = {2025}, organization = {IEEE/CVF}, doi = {https://doi.org/10.48550/arXiv.2412.04789}, url = {https://arxiv.org/abs/2412.04789}, }

IEEE

Object Semantics Give Us the Depth We Need: Multi-Task Approach to Aerial Depth Completion

Sara Hatami Gazani, Fardad Dadboud, Miodrag Bolic, Iraj Mantegh, and Homayoun Najjaran

2023

Bib

@article{gazani2023object,
  title = {Object Semantics Give Us the Depth We Need: Multi-Task Approach to Aerial Depth Completion},
  author = {Gazani, Sara Hatami and Dadboud, Fardad and Bolic, Miodrag and Mantegh, Iraj and Najjaran, Homayoun},
  booktitle = {2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)},
  pages = {2565--2570},
  year = {2023},
  organization = {IEEE},
}

A machine learning model for predicting favorable outcome in severe traumatic brain injury patients after 6 months

Mehdi Nourelahi, Fardad Dadboud, Hosseinali Khalili, Amin Niakan, and Hossein Parsaei

Acute and critical care, 2022

Bib

@article{nourelahi2022machine,
  title = {A machine learning model for predicting favorable outcome in severe traumatic brain injury patients after 6 months},
  author = {Nourelahi, Mehdi and Dadboud, Fardad and Khalili, Hosseinali and Niakan, Amin and Parsaei, Hossein},
  journal = {Acute and critical care},
  volume = {37},
  number = {1},
  pages = {45--52},
  year = {2022},
  publisher = {Korean Society of Critical Care Medicine},
}

Single-stage uav detection and classification with yolov5: Mosaic data augmentation and panet

Fardad Dadboud, Vaibhav Patel, Varun Mehta, Miodrag Bolic, and Iraj Mantegh

2021

Bib

@article{dadboud2021single,
  title = {Single-stage uav detection and classification with yolov5: Mosaic data augmentation and panet},
  author = {Dadboud, Fardad and Patel, Vaibhav and Mehta, Varun and Bolic, Miodrag and Mantegh, Iraj},
  booktitle = {2021 17th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)},
  pages = {1--8},
  year = {2021},
  organization = {IEEE},
}