Armaghan Moemeni

Uni-Light: An Ultra-Lightweight Framework via Uncertainty-Aware Knowledge Distillation for Brain Tumour Segmentation

A novel ultra-lightweight framework (Uni-Light) that achieves high-fidelity segmentation with substantially reduced computational overhead and advances data engineering for medical imaging by demonstrating that teacher model uncertainty can be exploited as a data-driven supervisory signal, re-prioritising the training...