Contact
| soumen@meta.com / mail.basu.s@gmail.com | |
| +1 646 842 6728/ | |
| Floor 43, 50 Hudson Yards, New York, NY 10001 | |
| LinkedIn Google Scholar |
About
Dr. Soumen Basu works in Computer Vision, Deep Learning, and Medical Image Analysis. He is particularly interested in learning with limited supervised data for safety-critical tasks. He completed his PhD at the Indian Institute of Technology (IIT) Delhi, where he pioneered AI-based models for detecting gallbladder cancer from ultrasound images. His innovative work has been published in top-tier conferences such as CVPR, MICCAI, and WACV as well as renowned journals like The Lancet Regional Health and Medical Image Analysis.
Dr. Basu is currently a Research Scientist at Meta New York, working in developing state-of-the-art Large Foundation Models for the Monetization teams. Prior to joining Meta, he was a Senior Chief Engineer at Samsung Research Bangalore, leading research in on-device Foundation Models for video and image-based segmentation. His previous experience includes roles at Adobe Systems and Penn State University. Dr. Basu has been awarded prestigious honors such as the Prime Minister's Research Fellowship and the Outstanding Teaching Assistant Award at IIT Delhi. He was also a recipient of the MICCAI STAR Award (2022).
Publications
-
Surpassing the Human Accuracy: Detecting Gallbladder Cancer from USG Images with Curriculum Learning
Soumen Basu, Mayank Gupta, Pratyaksha Rana, Pankaj Gupta, Chetan Arora
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June 2022.
[ Paper, Webpage ] -
Unsupervised Contrastive Learning of Image Representations from Ultrasound Videos using Hard Negative Mining
Soumen Basu, Somanshu Singla, Mayank Gupta, Pratyaksha Rana, Pankaj Gupta, Chetan Arora
25th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), September 2022.
[ Arxiv, Webpage ] -
RadFormer: Transformers with Global-Local Attention for Interpretable and Accurate Gallbladder Cancer Detection
Soumen Basu, Mayank Gupta, Pratyaksha Rana, Pankaj Gupta, Chetan Arora
Elsevier Medical Image Analysis (Impact Factor: 13.828)
[ Paper, Arxiv, Github ] -
Gallbladder Cancer Detection from US Images using only Image Level Labels
Soumen Basu, Ashish Papanai, Mayank Gupta, Pankaj Gupta, Chetan Arora
26th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), October 2023.
[ Arxiv, Webpage ] -
How reliable are the metrics used for assessing reliability in medical imaging?
Mayank Gupta, Soumen Basu, Chetan Arora
26th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), October 2023 (Oral selection).
[ Paper, Github ] -
Deep-learning enabled ultrasound based detection of gallbladder cancer in northern India: a prospective diagnostic study
Pankaj Gupta, Soumen Basu, et al.
The LANCET Regional Health, South-East Asia, 2023. (Impact Factor: 5.0)
[ Paper ] -
Deep learning models for differentiation of xanthogranulomatous cholecystitis and gallbladder cancer on ultrasound
Pankaj Gupta, Soumen Basu, et al.
Indian Journal of Gastroenterology, 2023. (Impact Factor: 2.0)
[ Paper ] -
Applications of artificial intelligence in biliary tract cancers
Pankaj Gupta, Soumen Basu, Chetan Arora
Indian Journal of Gastroenterology, 2024. (Impact Factor: 2.0)
[ Paper ] -
FocusMAE: Gallbladder Cancer Detection from Ultrasound Videos with Focused Masked Autoencoders
Soumen Basu, Mayuna Gupta, Chetan Madan, Pankaj Gupta, Chetan Arora
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June 2024.
[ Paper, Webpage ] -
LQ-Adapter: ViT-Adapter with Learnable Queries for Gallbladder Cancer Detection from Ultrasound Images
Chetan Madan, Mayuna Gupta, Soumen Basu, Pankaj Gupta, Chetan Arora
IEEE/ CVF Winter Conference on Applications of Computer Vision (WACV), February 2025.
[ Paper, Code ] -
Focus on Texture: Rethinking Pre-training in Masked Autoencoders for Medical Image Classification
Chetan Madan, Aarjav Satia, Soumen Basu, Pankaj Gupta, Usha Dutta, Chetan Arora
28th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), September 2025.
[ Paper, Code ]
Services
- Reviewer, MICCAI 2024
- Reviewer, ECCV 2024
- Reviewer, CVPR 2023, 2024
- Reviewer, WACV 2024, 2025
- Reviewer, IJCAI 2024
- Reviewer, ICCV 2023
- Reviewer, IPCAI 2023
- Program Committee Member, AAAI 2023, AAAI 2024
Recent Updates
- [09/2024] LQ-Adapter is accepted at WACV 2025 (round 1)!
- [08/2024] Convocated from IIT Delhi!
- [07/2024] Successfully Defended Ph.D. Thesis on 29-July-2024!!
- [07/2024] Serving as Reviewer at WACV 2025
- [06/2024] Attended CVPR 2024 in-person (Thanks CSE, IITD for funding!)
- [05/2024] Serving as Reviewer at MICCAI 2024
- [04/2023] Serving as Reviewer at ECCV 2024
- [03/2024] Started working with Samsung Research Bangalore as a Senior Chief Engineer (Visual Intelligence Team)
- [02/2024] Ph.D. Thesis submitted!
- [02/2024] FocusMAE is accepted at CVPR 2024!
- [01/2024] Ph.D. Synopsis presented
- [11/2023] Serving as Reviewer at CVPR 2024
- [11/2023] Paper accepted at Indian Journal of Gastroenterology
- [10/2023] Attended MICCAI 2023 in person and presented both Poster and Oral papers
- [08/2023] Paper accepted at LANCET Regional Health!
- [08/2023] Serving as Reviewer at WACV 2024
- [08/2023] Received Outstanding Teaching Assistant Award for Machine Learning course!
- [07/2023] Started working as an Applied Scientist Intern at Amazon
- [06/2023] Two papers accepted at MICCAI 2023!
- [04/2023] Serving as Reviewer in ICCV 2023
- [01/2023] Attending Google Research Week 2023 at Bangalore
- [11/2022] Serving as Reviewer in CVPR 2023 and IPCAI 2023
- [11/2022] Gave a talk at Ph.D. Seminar of Department of CSE, IIT Delhi
- [10/2022] RadFormer is Accepted at Elsevier Medical Image Analysis (IF: 13.828)!
- [09/2022] Served as Program Committee Member, AAAI 2023
- [06/2022] Attended MICCAI 2022 in person and presented our paper.
- [06/2022] Received MICCAI student travel award!
- [06/2022] Contrastive Learning is accepted for publication in MICCAI 2022! (Acceptance Rate: ~31%)
- [06/2022] Attended CVPR 2022 in person and presented GBCNet.
- [05/2022] Received CVPR DEI travel grant!
- [03/2022] GBCNet is accepted for publication in IEEE/CVF CVPR 2022! (Acceptance Rate: ~25%)
- [07/2021] Passed Ph.D. Comprehensive and moved to candidacy.
- [07/2021] Attended UCL Medical Image Computing Summer School (MedICSS), London, 2021 (Nominated by the Department, sponsored by IIT Delhi)
- [05/2021] Received the Pime Minister's Research Fellowship, Government of India, December 2020
- [12/2020] Winner (2nd Position) in ICVGIP-2020 Object Detection Challenge
- [12/2020] Attended ICVGIP, 2020, hosted by IIT Jodhpur
- [12/2020] Attended Amazon Research Day, 2020 (Virtual)
- [07/2020] Attended ICML, 2020 (Virtual)
Teaching
I have been a Teaching Assistant to the following courses. My responsibilities involved conducting lab sessions, assignment design, grading the assignments and exams.
- Machine Learning (COL341) [Received Outstanding TA Award]
- Cloud Computing Fundamentals (COL 733)
- Computer Vision (COL 780)
- Intro. to Computing (COL 100)
- Artificial Intelligence (COL 671)
- Software Engineering (COL 740)
- Data Structures and Algorithms (COL 106)
Others
- Instructions for using Vision Lab resources
- Template for Dissertation (CSE, IITD)
- Useful Scripts and Commands for Server Management