Md Mostafijur Rahman's Homepage

Portrait

Md Mostafijur Rahman

I am a Ph.D. Candidate at the The University of Texas at Austin working with Prof. Radu Marculescu. I am a member of System Level Design Group (SLD) @UT Austin. My research addresses computational inefficiency, data scarcity, model robustness, and generalizability in AI-driven biomedical imaging by designing efficient and accurate architectures, multi-modal learning systems, generative techniques, and data-efficient robust training methods for 2D/3D segmentation, synthesis, translation, denoising, and classification. By bridging the gap between AI advancements and clinical deployment, my work enables scalable, reliable solutions for real-world healthcare settings. My research accomplishments are evidenced by several impactful publications in top-tier venues, e.g., CVPR (2025, 2024), MIDL (2025, 2023), WACV (2025, 2024, 2023), ICASSAP 2025, etc. In the past, I have interned at National Institutes of Health (NIH) and Robert Bosch Research.

Prior to joining UT Austin, I was a Graduate Student in Software Engineering at University of Dhaka. I was advised by Prof. Mohammad Shoyaib. I have also spent four wonderful years as a faculty (Assistant professor and Lecturer) at University of Barishal. I had also an oppertunity to work as a Senior Software Enginner at Advanced Solution Lab, Samsung Research, Bangladesh.

Mail Scholar GitHub LinkedIn Resume/CV

Recent News

02/2025 1 paper (EffiDec3D) accepted to CVPR 2025.
02/2025 Attended UT System Trauma Research Symposium, 2025.
01/2025 Presented a poster at GAIN 2025 on "Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation".
12/2024 1 paper (MDNet) accepted to ICASSP 2025.
10/2024 1 paper (RapidNet) accepted to WACV 2025.
09/2024 1 abstract (Few-shot Image Denoising) accepted to EPFL Latsis Symposium on Smart Microscopy 2024 from internship at NIH.
08/2024 Gave a talk at NHLBI, NIH on "Efiicient Deep Learning for Biomedical Imaging".
08/2024 Presented a poster at NIH on "Universal Light Microscopy Denoising via Lightweight Multi-scale Convolutional Transformer".
07/2024 Won The Texas Health Catalyst Award 2024 for our "Medical Image Segmentation via Cascaded Attention Decoding".
05/2024 I have joined Office of AI Research (OAIR), NHLBI, NIH as 2024 Summer IRTA Fellow to work with Sarah Hopper and Christian Combs.
04/2024 1 paper (PP-SAM || [Code]) accepted to CVPRW 2024.
03/2024 Received the prestigious Summer IRTA Fellowship from Office of AI Research (OAIR), NHLBI, NIH to work with Sarah Hopper, Christian Combs, and Hui Xue.
02/2024 2 papers (EMCAD || [Code] and GreedyViG || [Code]) accepted to CVPR 2024.
01/2024 Presented a poster at GAIN 2024 on "Efficient Cascaded Graph Convolutional Decoding for 2D Medical Image Segmentation".
08/2023 1 paper (G-CASCADE) accepted to WACV 2024.
07/2023 Awarded Professional Development Fellowship by the Graduate School, UT Austin
05/2023 Spending Summer 2023 in Robert Bosch Research, Pittsburgh as Machine Learning Reseach Intern.
04/2023 Won the Ram’s Horn Best Project Award in Digital Video course by Prof. Alan Bovik, UT Austin.
03/2023 Received the Best Poster Award (for CASCADE) by Graduate and Industry Networking (GAIN), UT Austin.
03/2023 Presented a poster at GAIN 2023 on "Medical Image Segmentation via Cascaded Attention Decoding".
03/2023 1 paper (MERIT) accepted to MIDL 2023.
10/2022 1 paper (CASCADE) accepted to WACV 2023.
05/2022 Received the Feldman Graduate Research Fellowship, The University of Texas at Austin.
01/2022 I have started the Doctor of Philospohy in Electrical and Computer Engineering, The University of Texas at Austin (UT Austin). I have joined the System Level Design Group (SLD) advised by Prof. Radu Marculescu.

Selected Publication [Full List]

[CVPR 2025] EffiDec3D: An Optimized Decoder for Efficient High-Performance 3D Medical Image Segmentation.

Md Mostafijur Rahman, Radu Marculescu.

[Paper] [Code] Accepted
[MIDL 2025] Training-Free Dataset Pruning for Polyp Segmentation via Community Detection in Similarity Networks.

Md Mostafijur Rahman, Radu Marculescu.

[Paper] [Code]
[XXXXXX 2025] UltraLightUNet: Rethinking U-shaped Network with Multi-kernel Lightweight Convolutions for Medical Image Segmentation.

Md Mostafijur Rahman, Radu Marculescu.

[Paper] [Code]
[ICASSP 2025] MDNet: Multi-Decoder Network for Abdominal CT Organs Segmentation.

Debesh Jha, Nikhil Kumar Tomar, Koushik Biswas, Gorkem Durak, Matthew Antalek, Zheyuan Zhang, Bin Wang, Md Mostafijur Rahman, Hongyi Pan, Alpay Medetalibeyoglu, Yury Velichko, Daniela Ladner, Amir Borhani, Ulas Bagci.

[Paper] [Code]
[WACV 2025] RapidNet: Multi-Level Dilated Convolution Based Mobile Backbone.

Mustafa Munir, Md Mostafijur Rahman, and Radu Marculescu. [*GAIN Best Poster Award 2025 Winner]

[Paper] [Code]
[CVPR 2024] EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation.

Md Mostafijur Rahman, Mustafa Munir, and Radu Marculecu.

[Paper] [arxiv] [Code]
[CVPR 2024] GreedyViG: Dynamic Axial Graph Construction for Efficient Vision GNNs.

Mustafa Munir, William Avery, Md Mostafijur Rahman, and Radu Marculecu.

[Paper] [arxiv] [Code]
[CVPR 2024] PP-SAM: Perturbed Prompts for Robust Adaptation of Segment Anything Model for Polyp Segmentation.

Md Mostafijur Rahman, Mustafa Munir, Debesh Jha, Ulas Bagci, and Radu Marculescu.

[Paper] [arxiv] [Code]
[WACV 2024] G-CASCADE: Efficient Cascaded Graph Convolutional Decoding for 2D Medical Image Segmentation.

Md Mostafijur Rahman, Radu Marculescu.

[Paper] [arxiv] [Code]
[MIDL 2023] Multi-scale Hierarchical Vision Transformer with Cascaded Attention Decoding for Medical Image Segmentation.

Md Mostafijur Rahman, Radu Marculescu.

[Paper] [arxiv] [Code]
[WACV 2023] Medical Image Segmentation via Cascaded Attention Decoding.

Md Mostafijur Rahman, Radu Marculescu. [*GAIN Best Poster Award 2023 Winner, **The Texas Health Catalyst Award 2024 Winner]

[Paper] [Code]
[SIGSPATIAL GeoAI 2021] Mapping Road Safety Barriers Across Street View Image Sequences: A Hybrid Object Detection and Recurrent Model.

Md Mostafijur Rahman, Arpan Man Sainju, and Zhe Jiang.

[Paper] [Code]
[ICIEV 2019] Bangla Handwritten Basic Character Recognition Using Deep Convolutional Neural Network.

Chandrika Saha, Rahat Hossain Faisal, and Md Mostafijur Rahman.

[Paper] [Code]
[J-SIVP 2018] MCCT: a Multi-channel Complementary Census Transform for Image Classification.

Md Mostafijur Rahman, Shanto Rahman, and Mohammad Shoyaib.

[Paper] [Code]
[JIVP 2017] DTCTH: a Discriminative Local Pattern Descriptor for Image Classification.

Md Mostafijur Rahman, Shanto Rahman, Rayhanur Rahman, Mainul Hossain, and Mohammad Shoyaib.

[Paper] [Code]
[JIVP 2016] An Adaptive Gamma Correction for Image Enhancement.

Shanto Rahman, Md Mostafijur Rahman, M. Abdullah-Al-Wadud, Golam Dastegir Al-Quaderi, and Mohammad Shoyaib. [*Used by NIH in MIPAV API]

[Paper] [Code]
[ICCIT 2015] Noise Adaptive Binary Pattern for Face Image Analysis.

Md Mostafijur Rahman, Shanto Rahman, Minhas Kamal, M. Abdullah-Al-Wadud, Emon Kumar Dey, and Mohammad Shoyaib. [*Best Paper Award]

[Paper] [Code]

Teaching & Service

Teaching Assistant: EE319K Introduction to Embedded Systems course by Prof. Jonathan Valvano [UT Austin]
Conference Reviewer: CVPR 2025, ICLR 2025, NeurIPS 2024, MICCAI 2024, WACV 2024-2025, ISBI 2024-2025.
Journal Reviewer: PAMI, TMI, Pattern Recognition Letters, PLOS ONE.

Contact

Address

EER 5.838B
2501 Speedway
Austin, TX
United States
78712

Email

Academic
mostafijur.rahman [at] utexas.edu

Other Use
mostafij.csebu [at] gmail.com

Copyright © 2024 Md Mostafijur Rahman. All Rights Reserved.