Sourajit Saha

PhD Student at University of Maryland, Baltimore County

Email: ssaha2@umbc.edu Location: ITE 368, UMBC, Baltimore, MD 21250

Computer Vision | Machine Learning | Robust Visual Perception

Scene Understanding | Data Augmentation | Domain Generalization

Bio

I am currently pursuing PhD in Computer Science at University of Maryland, Baltimore County (UMBC). I am advised by Prof. Tejas Gokhale and I work on reliability in computer vision at the Perception Prediction and Reasoning Lab .

My current research focuses on two aspects of robustnes and reasoning in visual perception. I spend my time evaluating and improving computer vision systems to adapt to new domains, i.e. visual recognition module on Tesla developed and tested in sunny California should perform equally under change of domain, i.e. snowy Colorado. I investigate on leveraging LLMs and interpolation of images and latents in spectral domain to study domain generalization, domain adaptation, OOD detection, open-set recognition and, AI explainability.

Prior to joining UMBC, I was a Research Assistant at Center for Cognitive Skill Enhancement (CCSE) at Independent University Bangladesh (IUB). I have received a Masters of Science in Computer Science from UMBC in 2023 and a Bachelor of Science in Computer Science from BRAC University in 2017. In my free time I love composing EDMs, cooking and driving. If not computer science, I would have pursued stand up comedy!

News

Mar 2024: Got accepted into SCALE 2024 at JHU to work on event-based visual content retrieval on summer'24
Feb 2024: Guest lecture on CMSC 491/691: Computer Vision at UMBC
Feb 2024: Reviewing manuscripts for IJCAI 2024, ACM Transactions on Computing for Healthcare
Nov 2023: Guest lecture on CMSC 678: (Graduate) Machine Learning at UMBC
Oct 2023: Reviewing manuscripts for AAAI 2024 (student abstract)
Sep 2023: Joined Perception Prediction and Reasoning Lab, lead by Tejas Gokhale
Aug 2023: One paper accepted at ICCV 2023 in OODCV, Paris, France

Click to see older news

Publications

Most recent publications on Google Scholar.

Improving Shift Invariance in Convolutional Neural Networks with Translation Invariant Polyphase Sampling. Sourajit Saha, Tejas Gokhale

OOD-CV @ ICCV 2023 To appear soon

RFC-Net: Learning High Resolution Global Features for Medical Image Segmentation on a Computational Budget (Student Abstract). Sourajit Saha, Shaswati Saha, Md Osman Gani, Tim Oates, David Chapman

AAAI 2023 paper code

          @inproceedings{saha2023rfc,
            title={RFC-net: learning high resolution global features for medical image segmentation on a computational budget (student abstract)},
            author={Saha, Sourajit and Saha, Shaswati and Gani, Md Osman and Oates, Tim and Chapman, David},
            booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
            volume={37},
            number={13},
            pages={16314--16315},
            year={2023}
          }

Mitigating Domain Shift in AI-Based TB Screening With Unsupervised Domain Adaptation. Nishanjan Ravin, Sourajit Saha, Alan Schweitzer, Ameena Elahi, Farouk Dako, Daniel Mollura, David Chapman

IEEE Access paper code

          @article{ravin2022mitigating,
            title={Mitigating domain shift in AI-based TB screening with unsupervised domain adaptation},
            author={Ravin, Nishanjan and Saha, Sourajit and Schweitzer, Alan and Elahi, Ameena and Dako, Farouk and Mollura, Daniel and Chapman, David},
            journal={IEEE Access},
            volume={10},
            pages={45997--46013},
            year={2022},
            publisher={IEEE}
          }

Pairwise Meta Learning Pipeline: Classifying COVID-19 abnormalities on chest radio-graphs. Sourajit Saha, Yaacov Yesha, Yelena Yesha, Aryya Gangopadhyay, David Chapman, Michael Morris, Babak Saboury, Phuong Nguyen

SPIE Medical Imaging Conference 2022 Paper

          @article{saha2022pairwise,
            title={Pairwise meta learning pipeline: classifying COVID-19 abnormalities on chest radio-graphs},
            author={Saha, Sourajit and Yesha, Yaacov},
            journal={SPIE Medical Imaging 2022: Computer-Aided Diagnosis; PC1203302 (2022) Proceedings Volume PC12033, Medical Imaging 2022: Computer-Aided Diagnosis; PC1203302 (2022)},
            year={2022}
          }

A comprehensive set of novel residual blocks for deep learning architectures for diagnosis of retinal diseases from optical coherence tomography images. Sharif Amit Kamran, Sourajit Saha, Ali Shihab Sabbir, Alireza Tavakkoli

Springer Book Series, 2020 paper code

          @article{kamran2021comprehensive,
            title={A comprehensive set of novel residual blocks for deep learning architectures for diagnosis of retinal diseases from optical coherence tomography images},
            author={Kamran, Sharif Amit and Saha, Sourajit and Sabbir, Ali Shihab and Tavakkoli, Alireza},
            journal={Deep Learning Applications, Volume 2},
            pages={25--48},
            year={2021},
            publisher={Springer}
          }

Optic-Net: A Novel Convolutional Neural Network for Diagnosis of Retinal Diseases from Optical Tomography Images. Sharif Amit Kamran, Sourajit Saha, Ali Shihab Sabbir, Alireza Tavakkoli

ICMLA 2019 paper code

          @inproceedings{kamran2019optic,
            title={Optic-net: A novel convolutional neural network for diagnosis of retinal diseases from optical tomography images},
            author={Kamran, Sharif Amit and Saha, Sourajit and Sabbir, Ali Shihab and Tavakkoli, Alireza},
            booktitle={2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)},
            pages={964--971},
            year={2019},
            organization={IEEE}
          }

A Lightning fast approach to classify Bangla Handwritten Characters and Numerals using newly structured Deep Neural Network. Sourajit Saha, Nisha Saha

Procedia Computer Science, ELSEVIER Paper

          @article{saha2018lightning,
            title={A Lightning fast approach to classify Bangla Handwritten Characters and Numerals using newly structured Deep Neural Network},
            author={Saha, Sourajit and Saha, Nisha},
            journal={Procedia computer science},
            volume={132},
            pages={1760--1770},
            year={2018},
            publisher={Elsevier}
          }

Total recall: understanding traffic signs using deep convolutional neural network. Sourajit Saha, Sharif Amit Kamran, Ali Shihab Sabbir

ICCIT 2018 paper code

          @inproceedings{saha2018total,
            title={Total recall: understanding traffic signs using deep convolutional neural network},
            author={Saha, Sourajit and Kamran, Sharif Amit and Sabbir, Ali Shihab},
            booktitle={2018 21st international conference of computer and information technology (ICCIT)},
            pages={1--6},
            year={2018},
            organization={IEEE}
          }

Academic Service

Reviewer

Conferences: AAAI 2024, IJCAI 2024
Journals: APSIPA Transactions on Signal and Information Processing (Cambridge University Press), ACM Transactions on Computing for Healthcare

Membership

IEEE, AAAI, ACM, SPIE

Teaching

UMBC (TA + Guest Lecture): CMSC 691: Computer Vision Spring 2024:
UMBC (TA + Guest Lecture): CMSC 678: Machine Learning Fall 2023:
UMBC (TA): CMSC 471: Introduction to Artificial Intelligence Spring 2023:
UMBC (TA): CMSC 341: Data Structures Spring 2021:
UMBC (TA): CMSC 313: Assembly Language and Computer Organization Fall 2021:

Collaborators

Current Collaborators

Tejas Gokhale
Agneet Chatterjee

Previous Collaborators

Acknowledgement

Website theme inspirations: Aniruddha Saha, Martin Saveski, Aditi Partap.