no code implementations • 11 Apr 2024 • Sourajit Saha, Tejas Gokhale
Downsampling operators break the shift invariance of convolutional neural networks (CNNs) and this affects the robustness of features learned by CNNs when dealing with even small pixel-level shift.
1 code implementation • 18 Dec 2023 • Sourajit Saha, Shubhashis Roy Dipta
While the significance of discovering and introspecting the correlation between dataset statistics and AI model performance for dense prediction computer vision tasks such as semantic segmentation is well established in the computer vision literature, to the best of our knowledge, no visualization tools have been proposed to view and analyze the aforementioned tasks.
no code implementations • 13 Feb 2023 • Sourajit Saha, Shaswati Saha, Md Osman Gani, Tim Oates, David Chapman
Learning High-Resolution representations is essential for semantic segmentation.
no code implementations • 9 Nov 2021 • Nishanjan Ravin, Sourajit Saha, Alan Schweitzer, Ameena Elahi, Farouk Dako, Daniel Mollura, David Chapman
We show that without domain adaptation, ResNet-50 has difficulty in generalizing between imaging distributions from a number of public Tuberculosis screening datasets with imagery from geographically distributed regions.
2 code implementations • 13 Oct 2019 • Sharif Amit Kamran, Sourajit Saha, Ali Shihab Sabbir, Alireza Tavakkoli
Diagnosing different retinal diseases from Spectral Domain Optical Coherence Tomography (SD-OCT) images is a challenging task.
Ranked #1 on Retinal OCT Disease Classification on Srinivasan2014
1 code implementation • 30 Aug 2018 • Sourajit Saha, Sharif Amit Kamran, Ali Shihab Sabbir
Recognizing Traffic Signs using intelligent systems can drastically reduce the number of accidents happening world-wide.