20 papers
The Professor: Multi-Teacher Unsupervised Prompt Distillation for Vision-Language Models
Ahmad Algadhi, Ahmed Alzuhair, Omar Alkhulaif +1
Prompt distillation compresses large vision-language models (VLMs) such as CLIP into lightweight student models by matching teacher predictions on unlabeled domain images. PromptKD…
Hallucination in Medical Imaging AI: A Cross-Modality Analytical Framework for Taxonomy, Detection, and Mitigation under Regulatory Constraints
Omar Alshahrani, Muzammil Behzad
AI systems are being deployed across medical imaging faster than their failure modes are understood. At this point in time, the failure of greatest clinical concern is hallucinatio…
Spatio-Semantic Expert Routing Architecture with Mixture-of-Experts for Referring Image Segmentation
Alaa Dalaq, Muzammil Behzad
Referring image segmentation aims to produce a pixel-level mask for the image region described by a natural-language expression. Although pretrained vision-language models have imp…
XAI-CLIP: ROI-Guided Perturbation Framework for Explainable Medical Image Segmentation in Multimodal Vision-Language Models
Thuraya Alzubaidi, Sana Ammar, Maryam Alsharqi +2
Medical image segmentation is a critical component of clinical workflows, enabling accurate diagnosis, treatment planning, and disease monitoring. However, despite the superior per…
SwinTF3D: A Lightweight Multimodal Fusion Approach for Text-Guided 3D Medical Image Segmentation
Hasan Faraz Khan, Noor Fatima, Muzammil Behzad
The recent integration of artificial intelligence into medical imaging has driven remarkable advances in automated organ segmentation. However, most existing 3D segmentation framew…
Attack-Aware Deepfake Detection under Counter-Forensic Manipulations
Noor Fatima, Hasan Faraz Khan, Muzammil Behzad
This work presents an attack-aware deepfake and image-forensics detector designed for robustness, well-calibrated probabilities, and transparent evidence under realistic deployment…