Saeid Asgari
I am a Principal Machine Learning Research Scientist at Autodesk AI Research and an Adjunct Research Professor at the School of Computing Science (ranked #1 in Computer Vision in Canada), Simon Fraser University (SFU), Canada. Previously, I explored real-world machine learning and computer vision problems as a research scientist in startup environments.
I completed my PhD in Computing Science at SFU under the supervision of Prof. Ghassan Hamarneh. During my PhD I had multiple research visits/internships at different research institutions such as MILA (Montreal, Canada), Siemens Healtheneers (Princeton, USA), and Imagia (Montreal, Canada).
Outside of work, I have a strong passion for soccer and running track - the 100m sprint. I've had the privilege of competing and earning a few medals in inter-university competitions in these areas.
Email  / 
LinkedIn  / 
Google Scholar  / 
X
|
|
Research
My research is around developing interpretable and trustworthy (robust, reliable, and fair) machine learning systems that can handle domain shifts and spurious correlations without significant failures. Lately, my work has been focused on foundation models and leveraging language models for interpreting various models, including those related to vision. I am also actively working on addressing memorization issues in large generative models.
|
|
SLiMe: Segment Like Me
Optimzing textual embedings for single-shot object/part segmenation.
Aliasghar Khani, Saeid Asgari, Aditya Sanghi, Ali Mahdavi-Amiri, Ghassan Hamarneh
ICLR 2024
|
Selected Conference Publications
|
|
Select, Attend, and Transfer: Light, Learnable Skip Connections
Saeid Asgari ,
Aicha Bentaieb,
Anmol Sharma,
S. Kevin Zhou,
Yefeng Zheng,
Bogdan Georgescu,
Puneet Sharma,
Sasa Grbic,
Zhoubing Xu,
Dorin Comaniciu,
Ghassan Hamarneh,
MICCAI 2019, MLMI workshop (Oral presentation)
[paper]
|
|
Vulnerability Analysis of Chest X-Ray Image Classification Against Adversarial Attacks
Saeid Asgari ,
Arkadeep Das,
Ghassan Hamarneh,
MICCAI 2018, Understanding and Interpreting Machine Learning in Medical Image Computing applications workshop (Oral presentation)
[paper]
|
Seleted Journal Publications
|
|
Pareto-Optimal Multi-Objective Dimensionality Reduction Deep Auto-Encoder for Mammography Classification
Saeid Asgari ,
Jeremy Kawahara,
Ghassan Hamarneh,
Computer Methods and Programs in Biomedicine, 2017 (IF=7.10)
[paper]
|
|