4 papers
ECG-NAT: A Self-supervised Neighborhood Attention Transformer for Multi-lead Electrocardiogram Classification
Mahsa Gazeran, Sayvan Soleymanbaigi, Fatemeh Daneshfar +2
Electrocardiogram (ECG) arrhythmia classification remains challenging due to signal variability, noise, limited labeled data, and the difficulty in achieving both accuracy and effi…
GEM-FI: Gated Evidential Mixtures with Fisher Modulation
Marco Mustafa Mohammed, Fatemeh Daneshfar, Pietro Liò
Evidential Deep Learning (EDL) enables single-pass uncertainty estimation by predicting Dirichlet evidence, but it can remain overconfident and poorly calibrated, and it often fail…
TUR-DPO: Topology- and Uncertainty-Aware Direct Preference Optimization
Abdulhady Abas Abdullah, Fatemeh Daneshfar, Seyedali Mirjalili +1
Aligning large language models (LLMs) with human preferences is commonly done via reinforcement learning from human feedback (RLHF) with Proximal Policy Optimization (PPO) or, more…
BiCLIP: Bidirectional and Consistent Language-Image Processing for Robust Medical Image Segmentation
Saivan Talaei, Fatemeh Daneshfar, Abdulhady Abas Abdullah +1
Medical image segmentation is a cornerstone of computer-assisted diagnosis and treatment planning. While recent multimodal vision-language models have shown promise in enhancing se…