Portrait of Kaleem Siddiqi

Kaleem Siddiqi

Associate Academic Member
Professor, McGill University, School of Computer Science
Research Topics
Computational Biology
Computational Neuroscience
Computer Vision
Medical Machine Learning

Biography

Kaleem Siddiqi is a professor of computer science at McGill University and a member of McGill’s Centre for Intelligent Machines. He is also an associate academic member of Mila – Quebec Artificial Intelligence Institute, McGill’s Department of Mathematics and Statistics, and the Goodman Centre for Cancer Research at McGill. He holds an FRQS Dual Chair in Artificial Intelligence and Health with Keith Murai. Siddiqi’s research interests lie in computer vision, biological image analysis, neuroscience, visual perception and robotics. He is field chief editor for Frontiers in Computer Science and has served as an associate editor of IEEE Transactions on Pattern Analysis and Machine Intelligence, Pattern Recognition and Frontiers in ICT. He is co-author with Steve Pizer of the book Medial Representations: Mathematics, Algorithms and Applications (Springer, 2008).

Current Students

PhD - McGill University
Master's Research - McGill University
Master's Research - McGill University
PhD - McGill University
Master's Research - McGill University
Master's Research - McGill University
PhD - McGill University
Principal supervisor :
Undergraduate - McGill University
Master's Research - McGill University
PhD - McGill University
PhD - McGill University
Master's Research - McGill University
Master's Research - McGill University

Publications

Efficient Dynamics Modeling in Interactive Environments with Koopman Theory
Arnab Kumar Mondal
Siba Smarak Panigrahi
Sai Rajeswar
The accurate modeling of dynamics in interactive environments is critical for successful long-range prediction. Such a capability could adva… (see more)nce Reinforcement Learning (RL) and Planning algorithms, but achieving it is challenging. Inaccuracies in model estimates can compound, resulting in increased errors over long horizons. We approach this problem from the lens of Koopman theory, where the nonlinear dynamics of the environment can be linearized in a high-dimensional latent space. This allows us to efficiently parallelize the sequential problem of long-range prediction using convolution while accounting for the agent’s action at every time step. Our approach also enables stability analysis and better control over gradients through time. Taken together, these advantages result in significant improvement over the existing approaches, both in the efficiency and the accuracy of modeling dynamics over extended horizons. We also show that this model can be easily incorporated into dynamics modeling for model-based planning and model-free RL and report promising experimental results.
Interacting with a Visuotactile Countertop
M. Jenkin
Francois Hogan
Jean-François Tremblay
Bobak H. Baghi
Shape-Based Measures Improve Scene Categorization
Morteza Rezanejad
John Wilder
Dirk B. Walther
Allan D. Jepson
Sven Dickinson
Converging evidence indicates that deep neural network models that are trained on large datasets are biased toward color and texture informa… (see more)tion. Humans, on the other hand, can easily recognize objects and scenes from images as well as from bounding contours. Mid-level vision is characterized by the recombination and organization of simple primary features into more complex ones by a set of so-called Gestalt grouping rules. While described qualitatively in the human literature, a computational implementation of these perceptual grouping rules is so far missing. In this article, we contribute a novel set of algorithms for the detection of contour-based cues in complex scenes. We use the medial axis transform (MAT) to locally score contours according to these grouping rules. We demonstrate the benefit of these cues for scene categorization in two ways: (i) Both human observers and CNN models categorize scenes most accurately when perceptual grouping information is emphasized. (ii) Weighting the contours with these measures boosts performance of a CNN model significantly compared to the use of unweighted contours. Our work suggests that, even though these measures are computed directly from contours in the image, current CNN models do not appear to extract or utilize these grouping cues.
Multimodal and Force-Matched Imitation Learning with a See-Through Visuotactile Sensor
Trevor Ablett
Oliver Limoyo
Adam Sigal
Affan Jilani
Jonathan Kelly
Francois Hogan
Kinesthetic Teaching is a popular approach to collecting expert robotic demonstrations of contact-rich tasks for imitation learning (IL), bu… (see more)t it typically only measures motion, ignoring the force placed on the environment by the robot. Furthermore, contact-rich tasks require accurate sensing of both reaching and touching, which can be difficult to provide with conventional sensing modalities. We address these challenges with a See-Through-your-Skin (STS) visuotactile sensor, using the sensor both (i) as a measurement tool to improve kinesthetic teaching, and (ii) as a policy input in contact-rich door manipulation tasks. An STS sensor can be switched between visual and tactile modes by leveraging a semi-transparent surface and controllable lighting, allowing for both pre-contact visual sensing and during-contact tactile sensing with a single sensor. First, we propose tactile force matching, a methodology that enables a robot to match forces read during kinesthetic teaching using tactile signals. Second, we develop a policy that controls STS mode switching, allowing a policy to learn the appropriate moment to switch an STS from its visual to its tactile mode. Finally, we study multiple observation configurations to compare and contrast the value of visual and tactile data from an STS with visual data from a wrist-mounted eye-in-hand camera. With over 3,000 test episodes from real-world manipulation experiments, we find that the inclusion of force matching raises average policy success rates by 62.5%, STS mode switching by 30.3%, and STS data as a policy input by 42.5%. Our results highlight the utility of see-through tactile sensing for IL, both for data collection to allow force matching, and for policy execution to allow accurate task feedback.
Cardiomyocyte orientation recovery at micrometer scale reveals long‐axis fiber continuum in heart walls
Drisya Dileep
Tabish A Syed
Tyler FW Sloan
Perundurai S Dhandapany
Minhajuddin Sirajuddin
MLGCN: An Ultra Efficient Graph Convolution Neural Model For 3D Point Cloud Analysis
Mohammad Khodadad
Morteza Rezanejad
Ali Shiraee Kasmaee
Dirk Bernhardt-Walther
Hamidreza Mahyar
Organizing Principles of Astrocytic Nanoarchitecture in the Mouse Cerebral Cortex
Christopher K. Salmon
Tabish A Syed
J. Benjamin Kacerovsky
Nensi Alivodej
Alexandra L. Schober
Tyler F. W. Sloan
Michael T. Pratte
Michael P. Rosen
Miranda Green
Adario DasGupta
Shaurya Mehta
Affan Jilani
Yanan Wang
Hojatollah Vali
Craig A. Mandato
Keith K. Murai
Ultrastructure Analysis of Cardiomyocytes and Their Nuclei
Tabish A Syed
Yanan Wang
Drisya Dileep
Minhajuddin Sirajuddin
Predicting histopathology markers of endometrial carcinoma with a quantitative image analysis approach based on spherical harmonics in multiparametric MRI.
Thierry L. Lefebvre
Ozan Ciga
Sahir Rai Bhatnagar
Yoshiko Ueno
S. Saif
Eric Winter-Reinhold
Anthony Dohan
P. Soyer
Reza Forghani
Jan Seuntjens
Caroline Reinhold
Peter Savadjiev
Medial Spectral Coordinates for 3D Shape Analysis
Morteza Rezanejad
Mohammad Khodadad
Hamidreza Mahyar
Michael Gruninger
Dirk B. Walther
In recent years there has been a resurgence of interest in our community in the shape analysis of 3D objects repre-sented by surface meshes,… (see more) their voxelized interiors, or surface point clouds. In part, this interest has been stimulated by the increased availability of RGBD cameras, and by applications of computer vision to autonomous driving, medical imaging, and robotics. In these settings, spectral co-ordinates have shown promise for shape representation due to their ability to incorporate both local and global shape properties in a manner that is qualitatively invariant to iso-metric transformations. Yet, surprisingly, such coordinates have thus far typically considered only local surface positional or derivative information. In the present article, we propose to equip spectral coordinates with medial (object width) information, so as to enrich them. The key idea is to couple surface points that share a medial ball, via the weights of the adjacency matrix. We develop a spectral feature using this idea, and the algorithms to compute it. The incorporation of object width and medial coupling has direct benefits, as illustrated by our experiments on object classification, object part segmentation, and surface point correspondence.
Neural correlates of local parallelism during naturalistic vision
John Wilder
Morteza Rezanejad
Sven Dickinson
Allan Jepson
Dirk B. Walther
Human observers can rapidly perceive complex real-world scenes. Grouping visual elements into meaningful units is an integral part of this p… (see more)rocess. Yet, so far, the neural underpinnings of perceptual grouping have only been studied with simple lab stimuli. We here uncover the neural mechanisms of one important perceptual grouping cue, local parallelism. Using a new, image-computable algorithm for detecting local symmetry in line drawings and photographs, we manipulated the local parallelism content of real-world scenes. We decoded scene categories from patterns of brain activity obtained via functional magnetic resonance imaging (fMRI) in 38 human observers while they viewed the manipulated scenes. Decoding was significantly more accurate for scenes containing strong local parallelism compared to weak local parallelism in the parahippocampal place area (PPA), indicating a central role of parallelism in scene perception. To investigate the origin of the parallelism signal we performed a model-based fMRI analysis of the public BOLD5000 dataset, looking for voxels whose activation time course matches that of the locally parallel content of the 4916 photographs viewed by the participants in the experiment. We found a strong relationship with average local symmetry in visual areas V1-4, PPA, and retrosplenial cortex (RSC). Notably, the parallelism-related signal peaked first in V4, suggesting V4 as the site for extracting paralleism from the visual input. We conclude that local parallelism is a perceptual grouping cue that influences neuronal activity throughout the visual hierarchy, presumably starting at V4. Parallelism plays a key role in the representation of scene categories in PPA.
Neural correlates of local parallelism during naturalistic vision
John Wilder
Morteza Rezanejad
Sven J. Dickinson
A. Jepson
Dirk. B. Walther
Human observers can rapidly perceive complex real-world scenes. Grouping visual elements into meaningful units is an integral part of this p… (see more)rocess. Yet, so far, the neural underpinnings of perceptual grouping have only been studied with simple lab stimuli. We here uncover the neural mechanisms of one important perceptual grouping cue, local parallelism. Using a new, image-computable algorithm for detecting local symmetry in line drawings and photographs, we manipulated the local parallelism content of real-world scenes. We decoded scene categories from patterns of brain activity obtained via functional magnetic resonance imaging (fMRI) in 38 human observers while they viewed the manipulated scenes. Decoding was significantly more accurate for scenes containing strong local parallelism compared to weak local parallelism in the parahippocampal place area (PPA), indicating a central role of parallelism in scene perception. To investigate the origin of the parallelism signal we performed a model-based fMRI analysis of the public BOLD5000 dataset, looking for voxels whose activation time course matches that of the locally parallel content of the 4916 photographs viewed by the participants in the experiment. We found a strong relationship with average local symmetry in visual areas V1-4, PPA, and retrosplenial cortex (RSC). Notably, the parallelism-related signal peaked first in V4, suggesting V4 as the site for extracting paralleism from the visual input. We conclude that local parallelism is a perceptual grouping cue that influences neuronal activity throughout the visual hierarchy, presumably starting at V4. Parallelism plays a key role in the representation of scene categories in PPA.