Research
My main focus is in the intersection of computer vision, machine learning and image processing with applications
in visual perception and generation.
I'm developing data-driven learning-based algorithms that enable computers to accurately and
efficiently understand, model and recreate the visual world around us; all while reducing the need
for intensive manual labeling required to build intelligent systems. 🧠
I have a strong first-author publication record in top-tier conferences in my field,
like WACV and BMVC, high
impact factor journals like Transactions in Medical Imaging and Computers in
Biology and Medicine, as well as presented my research in prestigious conference workshops such
as CVPR,
ICML and MICCAI.
For my Ph.D research, I recieved the Doctoral Graduate Fellowship in addition to the
International Tuition Award of Excellence. In my MASc, I recieved the two-year MITACS Accelerate Fellowship. 🔬
I regularly contribute to open-source software and teaching. I have written feature code
in
YOLOv6,
Kornia and
a tutorial code in TensorFlow, Keras which also got featured in
Henry AI Labs. I've also built utility and fun tools like
Pynotify and
Boss Detector.
In my alma mater, NSU, I mentor (think Albus Dumbledore) undergrad baby scientists, specializing in machine learning which
involves guiding with: coding/programming, algorithm implementations, generating research questions, designing experiments and paper writing. 😬
I support Slow Science.
|
|
RSUD20K: A Dataset for Road Scene Understanding In Autonomous Driving
Authors : Hasib Zunair, Shakib Khan, A. Ben Hamza
arXiv, 2024
Paper /
Code /
Demo
RSUD20K is a new object detection dataset for road scene understanding, comprised of over 20K high-resolution images from
the driving perspective on Bangladesh roads, and includes 130K bounding box annotations for 13 objects. We benchmark recent object detectors
and explore Large Vision-Language models as image annotators.
|
|
Learning to Recognize Occluded and Small Objects with Partial Inputs
Authors : Hasib Zunair, A. Ben Hamza
IEEE/CVF Winter Conference on Applications of Computer Vision, 2024
Paper /
Code /
Website
We propose a learning algorithm to explicitly focus on context from neighbouring regions around objects
and learn a distribution of association across classes. Ideally to handle situations in-the-wild where only part of
some object class is visible, but where us humans might readily use context to infer the classes presence.
|
|
Masked Supervised Learning for Semantic Segmentation
Authors : Hasib Zunair, A. Ben Hamza
British Machine Vision Conference, 2022
(Oral Presentation)
Paper /
Code /
Poster /
Video
Masked Supervised Learning (MaskSup) is an effective single-stage learning paradigm
that models both short- and long-range context, capturing the contextual relationships between
pixels via random masking. Results show good segmentation performance, particularly at handling
ambiguous regions and retaining better segmentation of
minority classes with no added inference cost.
|
|
Fill in Fabrics: Body-Aware Self-Supervised Inpainting for Image-Based Virtual Try-On
Authors : Hasib Zunair, Samuel Mercier, Yan Gobeil, A. Ben Hamza
British Machine Vision Conference, 2022
Paper /
Code /
Poster /
Video
FIFA is a a self-supervised conditional generative adversarial network based framework
for virtual try-on. It consists of a Fabricator that aims to reconstruct the clothing image when provided with a masked clothing as input,
and learns the overall structure of the clothing by filling in fabrics. A
multi-scale structural constraint to enforce global context at multiple scales while
warping the target clothing to better fit the pose and shape of the person.
|
|
Quantifying imbalanced classification methods for leukemia detection
Authors : Deponker SarkerDepto, Md. Mashfiq Rizvee, Aimon Rahman, Hasib Zunair, M. Sohel Rahman, M.R.C. Mahdy
Computers in Biology and Medicine, 2022
Paper /
Code
Automated identification of leukemia from microscopic image is crucial for
early detection as the disease progresses rapidly. However, building these automated systems are challenging
owing to fine-grained variability of lymphoid precursor cells and imbalanced data points. We benchmark several
methods (input, loss amd GAN-based etc) 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
Authors : Md. Istiak Hossain Shihab†, Nazia Tasnim†, Hasib Zunair†, Labiba Kanij Rupty, Nabeel Mohammed († equal contribution)
AI City Challenge, CVPR Workshops, 2022
Paper /
Code /
Slides /
Leaderboard (3rd place)
Given a frame from a video sequence, we first segment single product item and hand followed
by entropy masking to address the domain bias problem, and then a
Vision Transformer (ViT) for multi-class classification. We also propose a custom metric that
discards frames not having any product items, utilizing several image
processing methods.Our method achieved 3rd place in the AI City Challenge, Track 4.
|
|
Knowledge distillation approach towards melanoma detection
Authors : Md Shakib Khan, Kazi Nabiul Istla, Abdur Rab Dhruba, Hasib Zunair, Nabeel Mohammed
Computers in Biology and Medicine, 2022
Paper /
Code
Proposed a knowledge distillation approach for melanoma detection to reduce model complexitiy and enable
easier deployment in edge devices. The proposed method requires relatively less time to detect melanoma. The method
is 15 times smaller than EfficientNet-B0 and consistently achieves better performance in both melanoma and non-melanoma detection.
|
|
Designing Efficient Deep Learning Models for Computer-Aided Medical Diagnosis
Authors: Hasib Zunair
Masters Thesis, 2021
Paper /
Code
Annotating medical image data is time consuming, costly and error prone, and
the scarcity of labeled data limits the effectiveness of supervised learning.
This thesis introduces generative modeling methods and architectures to address the scarcity of labels as well as
class imbalance which results in a bias towards to over-represented class for tasks
such as classification, binary and multi-class semantic segmentation.
|
|
Sharp U-Net: Depthwise convolutional network for biomedical image segmentation
Authors : Hasib Zunair, A. Ben Hamza
Computers in Biology and Medicine, 2021
Paper /
Code
Sharp U-Net achieves improved performance on six medical image segmentation datasets
in both binary and multi-class segmentation tasks while adding no extra learnable parameters.
The idea is instead of applying a plain skip connection,
a depthwise convolution of the encoder feature map with a sharpening kernel filter is done prior to merging the
encoder and decoder features.
|
|
STAR: Noisy Semi-Supervised Transfer Learning for Visual Classification
Authors : Hasib Zunair, Yan Gobeil, Samuel Mercier, A. Ben Hamza
ACM Workshop on Multimedia Content Analysis in Sports, 2021
(Oral Presentation)
Paper /
Code /
Decathlon Docs /
Blog Post /
Video
An efficient semi-supervised learning method is proposed for binary and multi-class image classification.
The method requires 6x less compute time and 5x less memory compared to prior arts. We also show that our method
boosts robustness of visual classification models, even without specifically optimizing for adversarial robustness.
|
|
MoNuSAC2020: A Multi-organ Nuclei
Segmentation and Classification Challenge
Authors : Ruchika Verma, Neeraj Kumar, Hasib Zunair, A. Ben Hamza and others.
IEEE Transactions on Medical Imaging (TMI), 2021
ISBI MoNuSAC Workshop, 2020 (Oral Presentation)
Paper /
Code /
Slides / Video (Time - 1:58:46) /
Leaderboard (11th place)
Automating the tasks of detecting, segmenting, and classifying cell nuclei can free up the pathologists’ time
for higher value tasks and reduce errors due to fatigue and subjectivity. 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
Authors : Hasib Zunair and A. Ben Hamza
ICML Workshop on Computational Biology, 2021 (Poster Presentation)
Social Network Analysis and Mining, 2021
Paper /
ICML WCB Short Paper /
Dataset
Propose synthetic image data by leveraging class conditioning and adversarial training that achieve results
comparable to training with only real data when using a test set of real images. Also combine synthetic data
with different sizes of real datasets for additional performance gains.
|
|
Automatic segmentation of blood cells from microscopic slides: A comparative analysis
Authors : 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
This work proposes a blood cell segmentation dataset consisting of multiple cell types.
Additionally, all cell types
do not have equal instances, which encourages researchers to develop algorithms for
learning from imbalanced classes in a few shot learning paradigm. We also provide both learning and non-learning based
methods as baselines.
|
|
Monocular-to-3D Virtual Try-On using Deep Residual U-Net
COMP 6381 Digital Geometric Modelling, Fall 2021
Project Page /
Code
Res-M3D-VTON is a pipeline for monocular to 3D virtual try-on (VTON)
for fashion clothing which uses residual learning to synthesize correct clothing parts,
preserve logo of clothing and reduce artifacts to finally output better textured
3D try-on meshes.
|
|
Dermatology Assistant
AI Model Code / REST API Code
This is a demonstration of a full stack deep learning project from training a model
to deploying it, using a REST API endpoint as well a separate end-user prototype web application. The
model is built for predicting the presence of melanoma from dermoscopic skin lesions using
neural networks.
|
|
Thyroid nodule segmentation from Ultrasound (US) images
Collaborators: Tajwar Abrar Aleef, Aimon Rahman and Labib Chowdhury
MICCAI TN-SCUI Challenge, 2020
In this work, several state-of-the-art image segmentation techniques were explored for optimizing
Thyroid Nodule segmentation from Ultrasound images. This inlcuded supervised learning, transfer learning,
and generative adversarial learning.
|
Machine Learning Competitions
Product Counting and Recognition for Retail Checkout, AI City Challenge, CVPR Workshop, 2022 (3rd Place)
Paper / Code / Leaderboard
Tuberculosis Type Classification, ImageCLEF, 2021 (2nd Place)
Paper / Code / Leaderboard
Nuclei Segmentation and Classification, 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
|
Invited Talks & Tutorials
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 December 2023.
|