LoFi RADIO: A Distilled In-Domain Backbone Applied for Artifact-Severity Grading of Ultra-Low-Field Neonatal Brain MR

The paper presents LoFi RADIO, a distilled ViT-S backbone designed for grading the severity of seven common artifacts in ultra‑low‑field neonatal brain MRI. It tackles the LISA 2026 Task 1a challenge by evaluating various backbones paired with a classification MLP, finding no single backbone dominates across all artifacts. The authors improve performance by routing complementary foundation model teachers through a per‑artifact gate and by distilling these teachers into the single in‑domain student, achieving comparable or better weighted composite scores without the need for multiple large models at inference.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.