AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

PhaseAT: Fourier Phase Adversarial Training for Medical Image Domain Generalization

arXiv · AI, language, vision and robotics · article · Oct 1, 2026 · UTC

Reliable clinical deployment of deep medical image models is hindered by distribution shifts across scanners, sites, and acquisition protocols. Existing domain generalization (DG) methods often focus on style or intensity diversification, but they can still leave networks dependent on domain-specific texture correlations. Inspired by evidence that Fourier phase encodes semantic structure, we introduce PhaseAT, a phase-aware adversarial training framework for medical DG. PhaseAT forms phase-perturbed training views in the Fourier domain by iteratively updating a bounded phase perturbation while

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-10-02T02:41:42.153Z. This is not the publication date.