I am a PhD Candidate at Ryerson University working with Dr. Neil Bruce and Dr. Kosta Derpanis in the Computer Vision Lab. I am also a Postgraduate Affiliate at the Vector Institute for Artificial Intelligence, Toronto. Previously, I received my MSc in Computer Science from the University of Manitoba, where I was advised by Dr. Yang Wang and Dr. Neil Bruce in the Computer Vision Lab. My research interests lie in computer vision and deep learning. Currently, I am mostly interested in understanding various properties of AI models beyond their performance, such as explainability, interpretability, generalization, fairness and bias.

Email: amirul [at] cs (dot) ryerson (dot) ca
CV / Google Scholar / GitHub / LinkedIn / Twitter



News



Publications & Preprints

Md Amirul Islam, Matthew Kowal, Sen Jia, Konstantinos G. Derpanis, Neil Bruce
Global Pooling, More than Meets the Eye: Position Information is Encoded Channel-Wise in CNNs
ICCV 2021
[arXiv] [Project Page] [Code] [Tweet]
Md Amirul Islam, Matthew Kowal, Konstantinos G. Derpanis, Neil D. B. Bruce
SegMix: Co-occurrence Driven Mixup for Semantic Segmentation and Adversarial Robustness
arXiv Preprint, 2021
[arXiv]
Md Amirul Islam, Matthew Kowal, Patrick Esser, Sen Jia, Björn Ommer, Konstantinos G. Derpanis, Neil Bruce
Shape or Texture: Understanding Discriminative Features in CNNs
ICLR 2021
[Project Page] [OpenReview] [arXiv] [Code] [Video] [Poster] [Slides] [News]
Md Amirul Islam, Matthew Kowal, Sen Jia, Konstantinos G. Derpanis, Neil Bruce
Position, Padding and Predictions: A Deeper Look at Position Information in CNNs
arXiv Preprint, 2021
[arXiv] [Project Page]
Shubhra Aich, Jean Vianney, Md Amirul Islam, Mannat Kaur, Bingbing Liu
Bidirectional Attention Network for Monocular Depth Estimation
ICRA 2021
[pdf] [video]
Zabir Al Nazi, Fazla Rabbi Mashrur, Md Amirul Islam, Shumit Saha
Fibro-CoSANet: Pulmonary Fibrosis Prognosis Prediction using a Convolutional Self Attention Network
arXiv Preprint, 2021
[pdf] [code]
Md Amirul Islam, Matthew Kowal, Konstantinos G. Derpanis, Neil Bruce
Feature Binding with Category-Dependant MixUp for Semantic Segmentation and Adversarial Robustness
BMVC 2020
[Project] [Paper] [Video]
Oral Presentation
Md Amirul Islam, Sen Jia, Neil Bruce
How much Position Information Do Convolutional Neural Networks Encode?
ICLR 2020
[Project] [OpenReview] [Paper] [Code] [Video]
Spotlight Presentation
Rezaul Karim, Md Amirul Islam, Neil Bruce
Distributed Iterative Gating Networks for Semantic Segmentation
WACV 2020
[Paper]
Mahmoud Kalash*, Md Amirul Islam*, Neil Bruce
[* Joint first authors]
Relative Saliency and Ranking: Models, Metrics, Data and Benchmarks
IEEE TPAMI, 2019
[Project] [Paper]
Rezaul Karim, Md Amirul Islam, Neil Bruce
Recurrent Iterative Gating Networks for Semantic Segmentation
WACV 2019
[Paper]
Md Amirul Islam, Mahmoud Kalash, Neil Bruce
Revisiting Salient Object Detection: Simultaneous Detection, Ranking, and Subitizing of Multiple Salient Objects
CVPR 2018
[Project] [Paper] [Code] [Video] [Poster]
Oral Presentation
Md Amirul Islam, Mahmoud Kalash, Neil Bruce
Semantics Meet Saliency: Exploring Domain Affinity and Models for Dual-Task Prediction
BMVC 2018
[Paper]
Md Amirul Islam, M Rochan, S Naha, Neil Bruce, Yang Wang
Gated Feedback Refinement Network for Coarse-to-Fine Dense Semantic Image Labeling
arXiv Preprint, 2018
[pdf]
Md Amirul Islam, M Rochan, Neil Bruce, Yang Wang
Gated Feedback Refinement Network for Dense Image Labeling
CVPR 2017
[Project] [Paper] [Code]
Rezaul Karim*, Md Amirul Islam*, Noman Mohammed, Neil Bruce
On the Robustness of Deep Learning Models to Universal Adversarial Attack
CRV 2018
[Paper]
Oral Presentation
Md Amirul Islam, M Kalash, M Rochan, Neil Bruce, Yang Wang
Salient Object Detection using a Context-Aware Refinement Network
BMVC 2017
[Project] [Paper]
Md Amirul Islam, S Naha, M Rochan, Neil Bruce, Yang Wang
Label Refinement Network for Coarse-to-Fine Semantic Segmentation
arXiv 2017
[pdf]
Md Amirul Islam, Neil Bruce, Yang Wang
Dense Image Labeling Using Deep Convolutional Neural Networks
CRV 2016, [Paper]
Oral Presentation