Mohammad Azam Khan, PhD

Current: Research Scientist | Kim Jaechul Graduate School of AI, KAIST.

Research Focus: Computer Vision, Medical Image Analysis, Healthcare.

Skills: Data Analytics, Machine Learning, Deep Learning, Python, PyTorch.

Kaggle: Competition Experts.

Work Experience

  • 12/2021 - Present

    Research Scientist

    Kim Jaechul Graduate School of AI, KAIST, South Korea.

  • 3/2009 - 11/2021

    Assistant/Subdivisional/Executive Engineer

    Dhaka Power Distribution Company Limited (DPDC), Bangladesh.

  • 3/2020 - 8/2020

    Postdoctoral Researcher

    Korea Advanced Institute of Science and Technology (KAIST), South Korea.

  • 6/2008 - 3/2009

    Teaching Assistant

    Bangladesh University of Engineering and Technology (BUET), Bangladesh.

Education

  • PhD 2020

    Computer Science and Engineering

    Korea University, Seoul, South Korea.

  • M. Engg. 2013

    Computer Science and Engineering

    Bangladesh University of Engineering and Technology (BUET), Dhaka, Bangladesh.

  • B. Sc. Engg. 2008

    Computer Science and Engineering

    International Islamic University Chittagong (IIUC), Chittagong, Bangladesh.

Selected Publications

Mining Multi-Label Samples from Single Positive Labels

Youngin Cho,* Daejin Kim,* Mohammad Azam Khan, and Jaegul Choo
Conference on Neural Information Processing Systems (NeurIPS), 2022.

WaveBound: Dynamically Bounding Error for Stable Time Series Forecasting

Youngin Cho,* Daejin Kim,* Dongmin Kim, Mohammad Azam Khan, and Jaegul Choo
Conference on Neural Information Processing Systems (NeurIPS), 2022.

Not just Compete, but Collaborate: Local Image-to-Image Translation via Cooperative Mask Prediction

DaeJin Kim, Mohammad Azam Khan, Jaegul Choo
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.

Development of Artificial Intelligence System for Quality Control of Photo Documentation in Esophagogastroduodenoscopy

Seong Ji Choi,* Mohammad Azam Khan,* Hyuk Soon Choi, Jaegul Choo, Jae Min Lee, and Soonwook Kwon (*: equal contributions)
Surgical Endoscopy, 2021 (IF: 3.149, as of 2019).

Automatic Detection of Tympanic Membrane and Middle Ear Infection from Oto-Endoscopic Images via Convolutional Neural Networks

Mohammad Azam Khan,* Soonwook Kwon,* Jaegul Choo, Seok Min Hong, Sung Hun Kang, Il-Ho Park, Sung Kyun Kim, and Seok Jin Hong (*: equal contributions)
Neural Networks, 126, Pages 384-394, 2020 (IF: 5.535, as of 2019)

Selected Competitions

2nd place among 11 teams.

Artefact detection Challenge (EAD 2019), ISBI 2019

Task: Multi-class artefact detection in video endoscopy

10th place among 29 actively participated teams.

Classification of Normal vs Malignant Cells in B-ALL White Blood Cancer

Task: Classification of leukemic B-lymphoblast cells from normal B-lymphoid precursors from blood smear microscopic images

12th place among 25 teams allowed for the final round.

Airbus Ship Detection Challenge | Kaggle

Task: Increase the accuracy and speed of automatic ship detection.

Position: 103/883 (Top 12%)

RSNA Pneumonia Detection Challenge | Kaggle

Task: Detect a visual signal for pneumonia in medical images.

Position: 62/1499 (Top 5%)

Mercedes-Benz Greener Manufacturing | Kaggle

Task: Tackle the curse of dimensionality and reduce the time that cars spend on the test bench.

Position: 73/3835 (Top 2%)

Intel & MobileODT Cervical Cancer Screening | Kaggle

Task: Develop an algorithm that accurately identifies a woman’s cervix type based on images.

Position: 38/848 (Top 5%)

Honors and Awards

  • Jun, 2021
    National ICT Awards 2020 - Champion (Research and Development)
    image
    In this category, a project is selected in the National ICT Awards for any Information and Communication Technology research and development, conducted by academic, non-academic institutions, or individuals to create innovative products, processes, and services. Such innovations are incomplete and yet to be marketed even though their features and functionalities can be demonstrated.

    The National ICT Awards is an annual event organized by the Bangladesh Association of Software and Information Services (BASIS) with the aim of showcasing and awarding innovative projects, ideas and solutions. Start-ups, SMEs, and entrepreneurs who have tapped into IT and ITES services to arrive at innovative solutions can participate in the BASIS National ICT award which comes with a wealth of opportunities. The ICT award event promises major boost and is an opportune platform for innovators within the ICT and ITES sectors. The award is nationally recognized and the winners of the National ICT Award can compete in the international awarding platform, namely The Asia Pacific ICT Alliance Awards, or APICTA in short.

    For details please visit: //bnia.basis.org.bd/

  • Jun, 2021
    National ICT Awards 2020 - Winner (Technology - Artificial Intelligence)
    image
    In this category, a project is selected in the National ICT Awards that address central problems or goals of AI research include reasoning, knowledge, planning, learning, natural language processing (communication), perception and the ability to move and manipulate objects.

  • Apr, 2019
    Travel Grant from University of Oxford and MedIAN
    image
    Presenter for Multi-class artefact detection in video endoscopy.

    ARTEFACT DETECTION CHALLENGE (EAD 2019), ISBI 2019, Venice, Italy, Mar/2019.

    Supported by: University of Oxford and MedIAN

    Featured interview

  • Feb, 2019
    HeLP Challenge 2018 - Awarded KRW 1,000,000
    image
    HeLP Challenge 2018

    2nd position in the “Ch1: Brain Tumor Segmentation” challenge

    ASAN Medical Center, Seoul, South Korea.

  • Sep, 2014
    Daffodil Japan IT Online Quiz Contest - 9th Place
    Daffodil Japan IT Ltd. organized an online quiz contest named “Daffodil Japan IT Online Quiz Contest” in September 2014. Final year undergraduates, graduates of IT as well as IT professionals were eligible to participate. More than 2000 participants, participated in this contest and the top 300 participants declared winners. Top most one got a laptop as a winning prize.
  • May, 2009
    ACI Pure Salt Deshke Jano Quiz Contest - Awarded BDT 100,000
    image
    Nationwide one of the ten top scorers

    ACI Pure Salt Deshke Jano Quiz Contest, 2009.

    Bangabandhu International Conference Center (BICC), Dhaka, Bangladesh.