Hasib Zunair / হাসিব জুনায়ের

I'm a Ph.D candidate at Concordia University working on contextual representation learning for computer vision applications. I also built end-to-end deep learning systems for sport use-cases at Décathlon and taught machine learning at Ericsson. 🧠

Previously, I did a two-year internship at Decathlon working on semi-supervised learning and generative AI. I did my MASc at Concordia, where I worked on medical image analysis. 👀

I like to read self-help books, cook fancy meals and spend time in nature. 🌿

I'm currently looking for roles in computer vision starting December 2024.

Email  /  CV  /  LinkedIn  /  Scholar  /  GitHub  /  Twitter

profile photo

Bio

I am an AI researcher and engineer, specializing in computer vision and machine/deep learning, with over 5 years of experience in both academia and industry. 🔬

My goal is to build and democratize AI systems that learn with less data and better understand the visual world around us. I am working to identify and overcome challenges in deploying computer vision tools, driven by their real-world potential, from self-driving cars, to assistive technologies, to healthcare. Specifically focussing on visual perception and generation, representation learning, and generalization. 🤖

I have created AI tools addressing complex real-world challenges in computer vision, for example, occlusions, small objects and data imbalance. I have several lead-author publications at top venues like WACV, BMVC, ICIP and IEEE TMI, and received awards like the MITACS Accelerate Fellowship. I've also built production-grade ML/CV solutions, from framing to deployment on cloud and on edge compute. I helped companies improve accuracy and efficiency of systems, increase user engagement, develop skills, cut costs, save time and resources. 🏭

Besides, I contribute to open-source software in top deep learning libraries like TensorFlow, Kornia & YOLOv6, take part in ML competitions like ImageCLEF Medical and AICITY at CVPR, and mentor numerous AI practitioners. I constantly learn to stay current in the field, and share them through writing articles and creating videos to help others grow in the field. 🧑‍🏫

I try to practice Slow Science.


Research

See also my Google Scholar profile for the most recent publications as well as the most-cited papers.

PEEKABOO: Hiding Parts of an Image for Unsupervised Object Localization
Hasib Zunair, A. Ben Hamza
British Machine Vision Conference, 2024
Paper / Code / Website

A segmentation model with zero-shot generalization to unfamiliar images and objects that are small, reflective or under poor illumination without the need for additional training.

RSUD20K: A Dataset for Road Scene Understanding In Autonomous Driving
Hasib Zunair, Shakib Khan, A. Ben Hamza
IEEE International Conference on Image Processing, 2024 (Oral Presentation)
Paper / Code / Demo

A dataset with 20K high-resolution images and 130K bounding box annotations. Benchmark object detectors and explore large vision language models (LVLMs) as image annotators.

Learning to Recognize Occluded and Small Objects with Partial Inputs
Hasib Zunair, A. Ben Hamza
IEEE/CVF Winter Conference on Applications of Computer Vision, 2024
Paper / Code / Website

Using masking to focus on context from neighbouring regions around objects and learn a distribution of association across classes, to better recognize occluded and small objects.

CosSIF: Cosine similarity-based image filtering to overcome low inter-class variation in synthetic medical image datasets
Mominul Islam, Hasib Zunair, Nabeel Mohammed
Computers in Biology and Medicine, 2024
Paper / Code

Data filtering algorithm based on cosine similarity to remove similar and redundant synthetic images from the minority class that resemble similarity to images from the majority class.

Masked Supervised Learning for Semantic Segmentation
Hasib Zunair, A. Ben Hamza
British Machine Vision Conference, 2022 (Oral Presentation)
Paper / Code / Poster / Video

A single-stage method that captures the contextual relationships between pixels via masking, shows good segmentation performance, especially in ambiguous regions and minority classes.

Fill in Fabrics: Body-Aware Self-Supervised Inpainting for Image-Based Virtual Try-On
Hasib Zunair, Samuel Mercier, Yan Gobeil, A. Ben Hamza
British Machine Vision Conference, 2022
Paper / Code / Poster / Video

A self-supervised generative adversarial network based framework for virtual try-on to handle complex person poses while retaining the texture and embroidery of clothing items.

Quantifying imbalanced classification methods for leukemia detection
Deponker SarkerDepto, Md. Mashfiq Rizvee, Aimon Rahman, Hasib Zunair, M. Sohel Rahman, M.R.C. Mahdy
Computers in Biology and Medicine, 2022
Paper / Code

We benchmark several methods designed to tackle class imbalance and find that loss-based methods outperform GAN-based and input-based methods for leukemia detection.

VISTA: Vision Transformer enhanced by U-Net and Image Colorfulness Frame Filtration for Automatic Retail Checkout
Md. Istiak Hossain Shihab, Nazia Tasnim, Hasib Zunair, Labiba Kanij Rupty, Nabeel Mohammed
IEEE/CVF Computer Vision and Pattern Recognition Workshop, 2022
Paper / Code / Slides / Leaderboard (3rd place)

A segmenter (U-Net) followed by a Vision Transformer (ViT) classifier for recognizing product items from videos. Our method achieved 3rd place in the AI City Challenge, Track 4.

Knowledge distillation approach towards melanoma detection
Md Shakib Khan, Kazi Nabiul Istla, Abdur Rab Dhruba, Hasib Zunair, Nabeel Mohammed
Computers in Biology and Medicine, 2022

Paper / Code

A knowledge distillation appraoch for melanoma detection to reduce model complexitiy and enable easy deployment in edge devices.

Designing Efficient Deep Learning Models for Computer-Aided Medical Diagnosis
Hasib Zunair
Masters Thesis, 2021
Paper / Code

Introduces various efficient deep learning architectures and generative modeling methods to address the scarcity of labels as well as class imbalance in biomedical image analysis.

Sharp U-Net: Depthwise convolutional network for biomedical image segmentation
Hasib Zunair, A. Ben Hamza
Computers in Biology and Medicine, 2021
Paper / Code

We propose to fuse encoder and decoder features in U-Nets using a sharpening kernel filter leading to improved performance on various medical image segmentation tasks.

STAR: Noisy Semi-Supervised Transfer Learning for Visual Classification
Hasib Zunair, Yan Gobeil, Samuel Mercier, A. Ben Hamza
International ACM Workshop on Multimedia Content Analysis in Sports, 2021
Paper / Code / Blog Post / Video

An efficient and robust semi-supervised learning method for image classification. It requires 6x less compute time and 5x less memory compared to prior arts.

ViPTT-Net: Video pretraining of spatio-temporal model for tuberculosis type classification from chest CT scans
Hasib Zunair, Aimon Rahman, and Nabeel Mohammed
Conference and Labs of the Evaluation Forum, 2021
Paper / Code / Leaderboard (2nd place)

Pretraining on videos for human activity recognition leads to better learning for tuberculosis type classification. This method was 2nd place in the ImageCLEF 2021 Medical.

MoNuSAC2020: A Multi-organ Nuclei Segmentation and Classification Challenge
Ruchika Verma, Neeraj Kumar, Hasib Zunair, A. Ben Hamza and others.
IEEE Transactions on Medical Imaging, 2021
Paper / Code / Slides / Video (Time - 1:58:46) / Leaderboard (11th place)

This paper summarizes and publicly releases the challenge dataset, and compile key findings of the methods developed by various participants.

Synthesis of COVID-19 Chest X-rays using Unpaired Image-to-Image Translation
Hasib Zunair and A. Ben Hamza
International Conference on Machine Learning Workshop, 2021
Social Network Analysis and Mining, 2021
Paper / ICML Workshop Ext. Abstract / Dataset

Generate synthetic image data by class conditioning and adversarial training to use as additional training data for imbalanced image classification.

Automatic segmentation of blood cells from microscopic slides: A comparative analysis
Deponker Sarker Depto, Shazidur Rahman, Md. Mekayel Hosen, Mst Shapna Akter, Tamanna Rahman Reme, Aimon Rahman, Hasib Zunair, M Sohel Rahman, M.R.C.Mahdy
Tissue and Cell, 2021
Paper / Dataset / Code

A blood cell segmentation dataset consisting of multiple cell types and benchmark of both learning and non-learning based methods.

A Comparative Analysis of Deep Learning Architectures on High Variation Malaria Parasite Classification Dataset
Aimon Rahman, Hasib Zunair, Tamanna Rahman Reme, M Sohel Rahman, M.R.C.Mahdy
Tissue and Cell, 2021
Paper

Transform a high variation malaria localization dataset to classification and benchmark several classification algorithm for malaria identification from microscopic images of red blood cells.

Uniformizing Techniques to Process CT scans with 3D CNNs for Tuberculosis Prediction
Hasib Zunair, Aimon Rahman, Nabeel Mohammed, and Joseph Paul Cohen
International Conference on Medical Image Computing and Computer Assisted Intervention Workshop, 2020
Paper / Code / Video

Analyzing 3D medical images in a per slice basis is a sub-optimal approach, that can be improved by 3D context. The method was ranked 5th in ImageCLEF Medical 2019.

Melanoma Detection using Adversarial Training and Deep Transfer Learning
Hasib Zunair and A. Ben Hamza
Physics in Medicine and Biology, 2020
Paper / Code

Improving fairness of medical classifiers and reduce data imbalance by enriching training datasets by generating synthetic under-represented class samples from over-represented ones.

Robust Deep Speaker Recognition: Learning Latent Representation with Joint Angular Margin Loss
Labib Chowdhury, Hasib Zunair and Nabeel Mohammed
Applied Sciences, 2020
Paper / Code

SincNet models consistently outperform prior models and generalizes well on unseen and diverse tasks such as Bengali speaker recognition.

Improving Malaria Parasite Detection from Red Blood Cell using Deep Convolutional Neural Networks
Aimon Rahman, Hasib Zunair, M Sohel Rahman, Jesia Quader Yuki, Sabyasachi Biswas, Md Ashraful Alam, Nabila Binte Alam, M.R.C. Mahdy
arXiv, 2019
Paper / Code

Benchmark several classification algorithms for malaria detection from microscopic images of red blood cells.

Estimating Severity from CT Scans of Tuberculosis Patients using 3D Convolutional Nets
Hasib Zunair, Aimon Rahman, Nabeel Mohammed
Conference and Labs of the Evaluation Forum, 2019
Paper / Code

A 3D CNN with a slice selection method to predict tuberculosis (TB) from chest CT images. Our method achieved 10-th place in the ImageCLEF 2019 Medical.

Unconventional Wisdom: A New Transfer Learning Approach Applied to Bengali Numeral Classification
Hasib Zunair, Nabeel Mohammed, Sifat Momen
International Conference on Bangla Speech and Language Processing, 2018
Paper / Code

A deep transfer learning approach that freezes intermediate layers for better accuracy on the NumtaDB Bengali handwritten digit dataset.

Design and Implementation of an Automated Web Based Multifunctional Attendance System
Hasib Zunair, Oishi Maniha, Jubayer Kabir
International Conference on Smart Sensors and Applications, 2018 (Best Student Paper)
Paper / Slides

Implementation of an automated multifunctional attendance system which uses rfid, fingerprint, and real time facial recognition.

Design and Implementation of an IOT based Monitoring System for Inland Vessels using Multiple Sensor Network
Hasib Zunair, Wordh Ul Hasan, Kimia Tuz Zaman, Irfanul Haque, Soumic Shekhar Aoyon
International Conference on Smart Sensors and Applications, 2018
Paper / Slides

A wireless sensor network with a real time web application for monitoring multiple ships to prevent catastrophic events due to overloading.

Design and Implementation of Security Patrol Robot using Android Application
Tahzib Mashrik, Hasib Zunair, Maofic Farhan Karin
Asia Modelling Symposium, 2017
Paper

A low-cost autonomous mobile security robot based on a multisensor system for the purpose of sending alarms remotely.



Machine Learning Competitions

Product Counting and Recognition for Retail Checkout, AI City Challenge, CVPR Workshop, 2022 (3rd Place)
Paper / Code / Leaderboard

Tuberculosis Type Classification from 3D CT Scans, ImageCLEF, 2021 (2nd Place)
Paper / Code / Leaderboard

Nuclei Segmentation and Classification from Whole Slide Images, MoNuSAC, 2020 (11th Place)
Paper / Code / Leaderboard

Tuberculosis Prediction, ImageCLEF, 2019 (5th Place)
Paper / Code / Leaderboard

Bengali Handwritten Digit Recognition, Bengali.AI, 2019 (6th Place)
Paper / Code / Leaderboard


Datasets

These include datasets I've created.

Bangladesh Road Scene Understanding Dataset for Autonomous Driving
Hasib Zunair, Shakib Khan, A. Ben Hamza
IEEE International Conference on Image Processing, 2024
Dataset Link

A dataset with 20K high-resolution images and 130K bounding box annotations. Benchmark object detectors and explore large vision language models (LVLMs) as image annotators.

Synthetic Dataset of COVID-19 Chest X-rays
Hasib Zunair and A. Ben Hamza
ICML Workshop on Computational Biology, 2021
Dataset Link

Collection of 21,295 synthetic COVID-19 chest X-ray images. The primary use of this dataset is to be used as additional data for training machine learning models.


Other Projects

These include coursework, side projects and unpublished research work.

Monocular-to-3D Virtual Try-On using Deep Residual U-Net
Hasib Zunair
COMP 6381 Digital Geometric Modelling, Fall 2021
Project Page / Code

A pipeline for monocular to 3D virtual try-on to synthesize correct clothing parts, preserve logo of clothing and reduce artifacts to finally output better textured 3D try-on meshes.

Low to high resolution knee MRI reconstruction
Hasib Zunair, Aimon Rahman
fastMRI Image Reconstruction Challenge, 2019

We use deep encoder-decoder architectures to reconstruct a high resolution knee MRI image given a low resolution MRI image.

Thyroid nodule segmentation from Ultrasound (US) images
Hasib Zunair, Tajwar Abrar Aleef, Aimon Rahman and Labib Chowdhury
MICCAI TN-SCUI Challenge, 2020

Benchmark several semantic segmentation methods for thyroid nodule segmentation task inlcuding supervised learning, transfer learning, and generative adversarial learning.


Tutorials & Invited Talks

Machine Learning Research Paper Writing Tutorial, 2024

Leveraging Vector Databases with Embeddings for Fast Image Search and Retrieval, 2024

Building and Applying Generative Models using PyTorch, Ericsson Canada, 2024

Build and Deploy Custom Docker Images for Object Recognition, Towards AI, 2023

Deep Learning in Computer Vision with PyTorch, 2023

Intro to Deep Learning with NumPy, NSU, 2022

Building ML models with TensorFlow, Ericsson Canada, 2021

How to get started with building Computer Vision systems, NSU, 2021

3D image classification from CT scans, Keras, TensorFlow, 2020

Programming with Python, NSU, 2019

Intro to Deep Learning for Image Classification using Python, NSU, 2019

Basics of Image Processing and Computer Vision, NSU, 2018

Intro to Robotics (ROBO101), a semester-long series of workshops, NSU, 2018


Template stolen from Jon Barron! Thanks for dropping by.
Last updated October 2024.