Ranking-Guided Semi-Supervised Domain Adaptation for Severity Classification
This addresses domain adaptation for severity classification in medical imaging, which is an incremental improvement over existing methods that struggle with ordered class labels.
The paper tackles the problem of severity classification in medical images under domain shift by proposing a semi-supervised domain adaptation method that uses ranking with class order to align source and target domains, achieving successful alignment of class-specific rank score distributions as validated on ulcerative colitis and diabetic retinopathy datasets.
Semi-supervised domain adaptation leverages a few labeled and many unlabeled target samples, making it promising for addressing domain shifts in medical image analysis. However, existing methods struggle with severity classification due to unclear class boundaries. Severity classification involves naturally ordered class labels, complicating adaptation. We propose a novel method that aligns source and target domains using rank scores learned via ranking with class order. Specifically, Cross-Domain Ranking ranks sample pairs across domains, while Continuous Distribution Alignment aligns rank score distributions. Experiments on ulcerative colitis and diabetic retinopathy classification validate the effectiveness of our approach, demonstrating successful alignment of class-specific rank score distributions.