Attention-Based Prototype Calibration for Multi-Rater Few-Shot Medical Image Segmentation
It addresses the problem of annotation variability across expert raters for few-shot medical image segmentation, offering a lightweight, compatible solution that improves personalized segmentation outputs.
The paper tackles multi-rater variability in few-shot medical image segmentation by introducing an attention-based prototype calibration framework that models rater-specific deviations from a consensus, achieving consistent improvements over baseline prototype methods on multi-rater datasets.
Few-shot medical image segmentation methods typically assume a single ground-truth annotation, overlooking systematic variability across expert raters commonly observed in clinical datasets. We propose an attention-based prototype calibration framework for few-shot multi-rater segmentation that models rater-specific deviations from a consensus representation in prototype space. A lightweight yet principled attention operator directly refines rater prototypes without modifying the backbone feature extractor, making the approach fully compatible with existing prototype-based few-shot segmentation methods. This design preserves semantic consistency while enabling personalized segmentation outputs with minimal computational overhead. Experiments on multi-rater medical imaging datasets demonstrate consistent improvements over baseline prototype approaches, highlighting the effectiveness of structured prototype calibration for modeling annotation variability. Our code is available at https://github.com/truong2710-cyber/JAPC.