Muhammad Kamran Janjua
Art is Long; Time is Fleeting!
I am a Machine Learning Researcher @ Huawei, Canada.
I work on video understanding and online learning problems.
Previously, I was a graduate student with Dr. Martha White at University of Alberta, where I worked on continual learning.
Email  / 
CV  / 
Google Scholar  / 
Github
|
|
Research
I am interested in problems in perception and learning, particularly in learning from videos. Some (representative) papers are highlighted.
|
|
Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone
Negar Hassanpour,
Muhammad Kamran Janjua,
Kunlin Zhang,
Sepehr Lavasani,
et. al.
Preprint, 2025
We propose ConicGrad, a principled, scalable, and robust MTL approach formulated as a constrained optimization problem. Our method introduces an angular constraint to dynamically regulate gradient update directions, confining them within a cone centered on the reference gradient of the overall objective.
|
|
Learning Truncated Causal History Model for Video Restoration
Muhammad Kamran Janjua,
Amirhosein Ghasemabadi,
Mohammad Salameh,
Di Niu
Neural Information Processing Systems (NeurIPS), 2024
We propose Turtle to learn the truncated causal history model for online video processing. The causal design in Turtle enables recurrence in inference through state-memorized historical features while allowing parallel training by sampling truncated video clips. We report new state-of-the-art results on a multitude of video restoration benchmark tasks.
|
|
CascadedGaze: Efficiency in Global Context Extraction for Image Restoration
Amirhosein Ghasemabadi,
Muhammad Kamran Janjua,
Mohammad Salameh,
Chunhua Zhou,
Fengyu Sun,
Di Niu
Transactions on Machine Learning Research (TMLR), 2024
We present CascadedGaze Network (CGNet), an encoder-decoder architecture that employs Global Context Extractor (GCE), a novel and efficient way to learn global information for image restoration.
|
|
GVFs in the Real World: Making Predictions Online for Water Treatment
Muhammad Kamran Janjua,
Haseeb Shah,
Martha White,
Erfan Miahi,
Marlos C Machado,
Adam White
Machine Learning, 2023
We show the importance of learning in deployment, by comparing a TD agent trained purely offline with no online updating to a TD agent that learns online. This final result is one of the first to motivate the importance of adapting predictions in real-time, for non-stationary high-volume systems in the real world.
|
|
Movement-Induced Priors for Deep Stereo
Yuxin Hou,
Muhammad Kamran Janjua,
Juho Kannala,
Arno Solin
25th International Conference on Pattern Recognition (ICPR), 2020
We propose a method for fusing stereo disparity estimation with movement-induced prior information.
|
|
Do Cross Modal Systems Leverage Semantic Relationships?
Shah Nawaz,
Muhammad Kamran Janjua,
Ignazio Gallo,
Arif Mahmood,
Alessandro Calefati,
Faisal Shafait
Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019
We propose a new measure SemanticMap to evaluate the performance of cross modal systems. Our proposed measure evaluates the semantic similarity between the image and text representations in the latent embedding space.
|
|
Git Loss for Deep Face Recognition
Muhammad Kamran Janjua*,
Alessandro Calefati*,
Shah Nawaz,
Ignazio Gallo
British Machine Vision Conference (BMVC), 2018
In order to further enhance the discriminative capability of deep features, we introduce a joint supervision signal, Git loss, which leverages on softmax and center loss functions. The aim of our loss function is to minimize the intra-class variations as well as maximize the inter-class distances.
|
|