Welcome

I'm Aliasghar Khani

Machine Learning Researcher

Aliasghar Khani

Machine Learning Researcher

Currently, I am pursuing a master's degree at Simon Fraser University, where I have the privilege of being supervised by Professor Ghassan Hamarneh, with Dr. Saeid Asgari as my co-supervisor. My academic journey began at Sharif University of Technology (SUT), where I completed my Bachelor's degree in Computer Engineering from 2016 to 2021, working under the guidance of Professor MohammadHossein Rohban for my B.S. project. During my B.S. project, I focused on leveraging self-supervised and weakly supervised methods to enhance adversarially trained models. This research aimed to address the challenges associated with adversarial training by exploring alternative learning approaches. Computer vision is my primary area of interest and research. I am particularly intrigued by the fundamental problems within this field, such as robustness and bias. Additionally, I have practical experience in combining language models with computer vision techniques, which has allowed me to explore the intersection of these domains. One of my greatest passions is continuous learning, and I am committed to utilizing my knowledge to tackle significant real-world problems, both through collaborative teamwork and individual efforts. In summary, my research interests encompass:

  • Robustness
  • Self supervised learning
  • Generalization

My Skills

Coding skills

Python
95%
C/C++
80%
JavaScript
60%
Matlab
70%

Other Skills

Mathematics Knowledge
80%
Machine Learning Knowledge
90%
Machine Learning Frameworks
90%

Education

  • 2021 - Current
    Computer Science
    Simon Fraser University

    M.Sc. student under supervision of Professor Ghassan Hamarneh

  • 2016 - 2021
    Computer Engineering
    Sharif University of Technology

    B.Sc. in Computer Engineering

  • 2012 - 2016
    Mathematics and Physics
    Shahid Madani High School

Experience

  • 2022
    AI Research Internship
    AutoDesk

    Under the supervision of Dr. Saeid Asgari

  • 2020 - 2021
    Research at Bioinformatics and Computational Biology (BCB) Lab
    Sharif University of Technology

    Under the supervision of Prof. Mohammad Hossein Rohban

  • 2019 - 2021
    AI Researcher
    Iran's National Elites Foundation

    Under the supervision of Prof. Mahdieh Soleymani Baghshah

Publication

SLiMe: Segment Like Me

ICLR2024

Semantic segmentation with an arbitrary granularity is a challenging task. We introduce SLiMe: Segment Like Me, which can segment an image according to a given sample by leveraging diffusion models' cross/self-attention and prompt optimization.

Link to paper

MaskTune : Mitigating Spurious Correlations by Forcing to Explore

NeurIPS2022

This work proposes MaskTune, a masking strategy that prevents over-reliance on spurious (or a limited number of) features. MaskTune forces the trained model to explore new features during a single epoch finetuning by masking previously discovered features. MaskTune, unlike earlier approaches for mitigating shortcut learning, does not require any supervision.

Link to paper

Counterbalancing Teacher: Regularizing Batch Normalized Models for Robustness

arXiv2022

In this work, we investigate low generalization performance for BN by first showing that removing BN layers across a wide range of architectures leads to lower out-of-domain and corruption errors at the cost of higher in-domain errors. We then propose Counterbalancing Teacher (CT), for increasing robustness.

Link to paper

PAIP 2020: Microsatellite instability prediction in colorectal cancer

Medical Image Analysis

In this work, we introduce the PAIP 2020 challenge, which addresses colon cancer cases affected by MSI (micro-satellite instability). To our knowledge, this is the inaugural challenge that integrates image segmentation and genetic data. This paper encompasses details about the organizing team's activities, the colon cancer cohort, measurement methodologies, participant algorithms, and a comprehensive evaluation of each algorithm's performance. Additionally, this paper presents the algorithms utilized by the top 10 ranked participants in the challenge.

Link to paper

MoNuSAC2020: A multi-organ nuclei segmentation and classification challenge

IEEE Transactions on Medical Imaging 2021

Automating the tasks of detecting, segmenting, and classifying nuclei can free up the pathologists' time for higher value tasks and reduce errors due to fatigue and subjectivity. We prepared a large and diverse dataset of nucleus boundary annotations and class labels and organized a challenge around this dataset. In this paper, we summarize the dataset and the key findings of the challenge.

Link to paper

A Deep Learning Framework for Viable Tumor Burden Estimation

ICSPIS2020

In this paper, we propose a deep-learning framework for the segmentation of whole and viable tumor areas of liver cancer from whole-slide images (WSIs). To this end, we use a Fast Segmentation Convolutional Neural Network (Fast-SCNN) as our network. After data-augmentation on the training subset, we train the network with a multi-term loss function and SWA technique.

Link to paper

Towards automatic prostate gleason grading via deep convolutional neural networks

ICSPIS2019

In terms of accuracy, microscopic inspection of biopsy tissues is best. The Gleason grading system is used to evaluate the stage of prostate cancer using prostate biopsy samples. It is time-consuming to grade each region in a tissue. In this paper, we propose an automatic method for this task based on a deep learning-based approach. The MobileNetV2 backbone is used with the DeepLabV3+ model.

Link to paper
Projects

See my work

Information Retrieval System

Indexes Wikipedia's Data with text classification, clustering system, and a crawler that crawls pages and indexes in ElasticSearch.

Hospital Patients Reception Simulation

Simulator for the Reception of patients in a hospital.

IoT Monitoring Device

IoT device fro measuring soil temperature and humidity in the greenhouse and sends them to a web server.

Corona Virus Segmentation and Classification

Researched segmentation and classification of coronavirus in CT-scan images.

Cancerous Area Detection Website

Website for analyzing histopathology tissue images and detects cancerous portions.

Bag of Classifiers

We implemented Perceptron, MIRA, and Kernelized classifiers in python on MNIST and fashion datasets.