From the 2 of 13 linked papers with an AI index.
13 papers
SARFA: Segment Anything with Radiomic Feature Alignment
Tyler Ward, Abdullah Imran
The paper introduces SARFA, a framework that improves ambiguous medical image segmentation by generating multiple candidate masks and aligning them with radiomic features using Fré…
Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training?
Nusrat Munia, Tyler Ward, Nishat Nayla +2
The paper empirically compares pretraining‑finetuning and joint training of self‑supervised and supervised objectives across multiple SSL methods and vision tasks, showing that joi…
Protecting and Preserving Protest Dynamics for Responsible Analysis
Cohen Archbold, Usman Hassan, Nazmus Sakib +2
Protest-related social media data are valuable for understanding collective action but inherently high-risk due to concerns surrounding surveillance, repression, and individual pri…
Domain and Task-Focused Example Selection for Data-Efficient Contrastive Medical Image Segmentation
Tyler Ward, Aaron Moseley, Abdullah-Al-Zubaer Imran
Segmentation is one of the most important tasks in the medical imaging pipeline as it influences a number of image-based decisions. To be effective, fully supervised segmentation a…
EarthScape: A Multimodal Dataset for Surficial Geologic Mapping and Earth Surface Analysis
Matthew Massey, Nusrat Munia, Abdullah-Al-Zubaer Imran
Surficial geologic (SG) maps are essential for understanding surface processes and supporting infrastructure planning, but current workflows are labor-intensive and difficult to sc…
CAP-IQA: Context-Aware Prompt-Guided CT Image Quality Assessment
Kazi Ramisa Rifa, Jie Zhang, Abdullah Imran
Prompt-based methods, which encode medical priors through descriptive text, have been only minimally explored for CT Image Quality Assessment (IQA). While such prompts can embed pr…