Zahra Gharaee

Skills

• Programming Languages

  • Python
  • C++

• Big Data Analysis

  • Pandas
  • Apache Spark (Pyspark)

• Machine Learning Frameworks

  • Scikit-learn
  • Pytorch
  • TensorFlow

• Transformers

  • SWIN
  • DETR
  • ViT

• Large Language Models (LLMs)

  • GPT
  • BERT
  • Flan-T5

• Fine-tuning & Reinforcement Learning

  • PEFT LoRA
  • RLHF
  • PPO

• Cloud Computing & Storage

  • AWS
  • GCP
  • Digital Research Alliance of Canada
  • SNIC

• Computer Vision

  • OpenCV
  • Pillow
  • PIL

• Graph & Spatial Data Processing

  • NetworkX
  • OSMnx
  • Shapely

• Data Visualization

  • Matplotlib
  • Plotly
  • Seaborn

• Version Control Framework

  • Git

• Containerization

  • Docker
  • Singularity

• Simulator

  • CARLA
  • Webots

• Soft Skills

  • Problem-Solving
  • Detail Oriented
  • Agile Development
  • Teamwork
  • Report and Presentation
  • Project Leadership
  • Project Management
  • Accountability
  • Collaboration

Experience

Projects

BIOSCAN-5M

About: Led the creation of a 5M-image multimodal dataset with standardized metadata, scalable preprocessing, and Hugging Face integration. Enabled robust ML experimentation, multimodal benchmarking, and large-scale taxonomic and statistical analysis.

Keywords: Biotechnology - Data science - Statistical processing, Supervised learning - Unsupervised learning - BERT - CLIP - Contrastive learning - Zero-shot clustering

View Project

SuperFormer

About: A Transformer-based model that leverages superpixels for efficient Salient Object Detection (SOD).

Keywords: SWIN Transformer - Multimodal feature Representation - Efficient salient object detection - Fine-tuning - Pre-training - Fourier transformers

View Project

BIOSCAN-1M

About: Developed a large-scale, taxonomy-aware insect image dataset with automated ML pipelines, robust model benchmarking (ResNet50, ViT), and reproducible evaluation across diverse experimental settings.

Keywords: Biotechnology - Data science - Vision transformers - Object detection - Big data analytics - Fine-tuning - Transfer Learning

View Project

Causality

About: Two approaches to generative and implicit causal representation learning.

Keywords: Causal inference - Representation learning - Generative models - Domain Adaptation - Domain generalization - Interventions - Variational autoencoders

View Project

MoE-VRD

About: Collaborated with Microsoft Media Group on modeling subject-object interactions in visual scenes. Developed and refined a framework for action recognition and scene understanding.

Keywords: Computer Vision - Scene graph generation - Video relationship detection - Mixture of experts

View Project

SLOPE-KP

About: Co-led a project on 3D shape reconstruction and pose prediction from single images using self-supervised learning. Developed and evaluated a keypoint-based pipeline across static and dynamic datasets, achieving notable gains in accuracy and generalization.

Keywords: Computer vision - 3D shape reconstruction - Pose estimation - 3D Rotation

View Project

GAIN

About: An approach to graph representation learning.

Keywords: Graph neural networks - Representation learning - Geospatial data analysis - Classification - Road network graphs - Urban infrastructure

View Project

BRL-VBVC

About: An approach to Bayesian Reinforcement Learning of vision-based vehicular control.

Keywords: Autonomous systems - Reinforcement learning - Simulated environment - Semantic segmentation - Bayesian RL

View Project

Education

Certificates

Public Speaking

Selected Publications

• BIOSCAN-5M: A Multimodal Dataset for Insect Biodiversity

  Authors: Zahra Gharaee, Scott C Lowe, ZeMing Gong, Pablo Millan Arias, Nicholas Pellegrino, Austin T Wang, Joakim Bruslund Haurum, Iuliia Zarubiieva, Lila Kari, Dirk Steinke, Graham W Taylor, Paul Fieguth, Angel X Chang

  Advances in Neural Information Processing Systems (NeurIPS), 2024.

  View Publication

• A Step Towards Worldwide Biodiversity Assessment: The Bioscan-1M Insect Dataset

  Authors: Zahra Gharaee, ZeMing Gong, Nicholas Pellegrino, Iuliia Zarubiieva, Joakim Bruslund Haurum, Scott Lowe, Jaclyn McKeown, Chris Ho, Joschka McLeod, Yi-Yun Wei, Jireh Agda, Sujeevan Ratnasingham, Dirk Steinke, Angel Chang, Graham W Taylor, Paul Fieguth

  Advances in Neural Information Processing Systems (NeurIPS), 2023.

  View Publication

• Generative Causal Representation Learning for Out-of-Distribution Motion Forecasting

  Authors: Shayan Shirahmad Gale Bagi, Zahra Gharaee, Oliver Schulte, Mark Crowley

  International Conference on Machine Learning (ICML), 2023.

  View Publication

• Video Relationship Detection Using Mixture of Experts

  Authors: Ala Shaabana, Zahra Gharaee, Paul Fieguth

  IEEE Access, 2023.

  View Publication

• Self-supervised Learning of Object Pose Estimation Using Keypoint Prediction

  Authors: Zahra Gharaee, Felix Järemo Lawin, Per-Erik Forssén

  arXiv preprint arXiv:2302.07360, 2023.

  View Publication

• Graph Representation Learning for Road Type Classification

  Authors: Zahra Gharaee, Shreyas Kowshik, Oliver Stromann, Michael Felsberg

  Pattern Recognition, 2021.

  View Publication

• A Bayesian Approach to Reinforcement Learning of Vision-Based Vehicular Control

  Authors: Zahra Gharaee, Karl Holmquist, Linbo He, Michael Felsberg

  25th International Conference on Pattern Recognition (ICPR), 2021.

  View Publication

• Hierarchical Growing Grid Networks for Skeleton Based Action Recognition

  Authors: Zahra Gharaee

  Cognitive Systems Research, 2020.

  View Publication

• First and Second Order Dynamics in a Hierarchical SOM System for Action Recognition

  Authors: Zahra Gharaee, Peter Gärdenfors, Magnus Johnsson

  Applied Soft Computing, 2017.

  View Publication