SOURCE-LINKED INTELLIGENCE

Beyond Classification: Structured Supervision Aligns Visual Evidence with Medical Semantics

arXiv · AI, language, vision and robotics · article · Sep 5, 2026 · UTC

Vision Transformers (ViTs) have shown immense potential in medical image analysis. However, standard pre-training via global image classification suffers from spatial collapse, where models rely heavily on background shortcuts rather than localising critical foreground lesions. To overcome this limitation and align visual evidence with precise medical semantics, we systematically investigate alternative pre-training paradigms.Specifically, we evaluate three independent forms of structured supervision: topological priors via graph self-supervision, dense pixel-level constraints via segmentation

Read original source ↗ Open in workspace

recordType

paper

region

Global