|
Hi! I am currently a Ph.D student with Graduate Doctoral Fellowship, working on computer vision and machine learning advised by Prof. A. Ben Hamza at Concordia University, Montreal, Canada. I did my Masters at Concoridia where I focussed on the limitations of medical applications of computer vision. During my masters, I also recieved the two-year MITACS Accelerate Fellowship to work jointly with Concordia and Décathlon as a research intern on semi-supervised learning for object recognition. I've also spent time at Think Bricks LLC exploring applications of computer vision in medical image analysis and at The Tech Academy building robots! 🤖 During my bachelors at North South University in Bangladesh, I was first exposed to research when I was advised by Prof. Nabeel Mohammed. I served as the founding chair of IEEE Robotics and Automation Society (RAS) Student Branch Chapter which is the first RAS student chapter in Bangladesh. I like to cook fancy meals (beauty is in the eye of the beholder) and play e-sports, Dota 2 and CSGO, during my free time. I also like funny dog videos! 🐕 Email / LinkedIn / GitHub / Google Scholar / Twitter |
|
|
My research interests lies at the intersection of computer vision and machine learning, with the goal of building human-level computer vision systems that can understand, model, and recreate the visual world around us. I am working on algorithms for visual perception, synthesis (object recognition, segmentation, generation, ...) and representation learning (pre-training networks with strong, weak, or no supervision, ...) to reduce the need for intensive manual labeling efforts. 🧠 👀 I have a passion for AI, automation, open-source software and teaching. I have contributed code to Keras that demonstrates a deep learning workflow on 3D Image Classification from CT Scans, which also got featured in a video by Henry AI Labs. I've also built some projects including Pynotify: A Python package to send emails and Boss Detector: Changes monitor screen when your boss is near 😬 . I support Slow Science. |
|
See also my Google Scholar profile for the most recent publications as well as the most-cited papers. |
|
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 methods 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 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. |
|
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. |
|
We pretrain a model on videos for human activity recognition which leads to better representations for the downstream tuberculosis type classification task, especially for under-represented class samples. Our method achieved 2nd place in the ImageCLEF 2021 Tuberculosis Type Classification Challenge. |
|
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. |
|
Propose the first-of-its-kind open dataset of synthetic COVID-19 chest X-ray images using unsupervised domain adaptation by leveraging class conditioning and adversarial training. |
|
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. |
|
Transformed a high variation malaria localization dataset into a malaria classification dataset. Several classification algorithm benchmarks are provided for the task of classifying presence of malaria from microscopic images of isolated red blood cells. |
|
Showed that analyzing 3D medical images in a per slice basis is a sub-optimal approach, that can be improved by 3D context. Ranked 5-th in ImageCLEF 2019. |
|
Improved classification performance by synthesizing under-represented class samples from the over-represented ones. Synthetic samples are used as additional training data to reduce class imbalance. |
|
SincNet models based on joint angular margin loss not only consistently outperformed current prior models, but also generalizes well on unseen and diverse tasks such as Bengali speaker recognition. |
|
Benchmarked several classification algorithms for the task of detecting malaria from microscopic images of red blood cells. Transfer learning approach worked best in our study. |
|
A 3D CNN with a slice selection method employed in the task of chest CT image analysis for predicting tuberculosis (TB). Our method achieved 10-th place in the ImageCLEF 2019 Tuberculosis SVR - Severity scoring. |
|
An accuracy of 97.09% was achieved on the NumtaDB Bengali handwritten digit dataset, which was obtained by freezing intermediate layers. |
|
Implementation of an automated multifunctional attendance system which uses rfid, fingerprint, and real time facial recognition. |
|
A wireless sensor network with a real time web application for monitoring multiple ships to prevent catastrophic events due to overloading. |
|
A low-cost autonomous mobile security robot based on a multisensor system for the purpose of sending alarms remotely. |
|
|
|
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. |
|
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. |
|
Authors: Hasib Zunair and 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. |
|
Authors: Hasib Zunair, 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. |
|
|
 |
Lab Demonstrator, COMP 6771: Image Processing, Winter 2022
Lab Demonstrator, COMP 333: Intro to Data Analytics, Fall 2021 Lab Demonstrator, COMP 6771: Image Processing, Winter 2021 |
 |
Presenting tutorials to Ericsson employees relevant to the projects as well as suggesting relevant software tools for the projects. Also support project implementations and ensure correctness of project approaches and results. Article / Tutorials |
|
Student Instructor, Image Classification with Python and Keras, Fall 2019
Student Instructor, Introduction to Python Programming, Winter 2019 Student Instructor, Image Processing and Computer Vision, Fall 2018 |