Reference-guided Pseudo-Label Generation for Medical Semantic Segmentation

Producing densely annotated data is a difficult and tedious
task for medical imaging applications. To address this prob-
lem, we propose a novel approach to generate supervision for
semi-supervised semantic segmentation. We argue that visu-
ally similar regions between labeled and unlabeled images
likely contain the same semantics and therefore should share
their label. Following this thought, we use a small number of
labeled images as reference material and match pixels in an
unlabeled image to the semantics of the best fitting pixel in
a reference set. This way, we avoid pitfalls such as confirma-
tion bias, common in purely prediction-based pseudo-labeling.
Since our method does not require any architectural changes or
accompanying networks, one can easily insert it into existing
frameworks. We achieve the same performance as a standard
fully supervised model on X-ray anatomy segmentation, albeit
95% fewer labeled images. Aside from an in-depth analy-
sis of different aspects of our proposed method, we further
demonstrate the effectiveness of our reference-guided learning
paradigm by comparing our approach against existing methods
... mehr
for retinal fluid segmentation with competitive performance
as we improve upon recent work by up to 15% mean IoU.