Discrepancy Matters: Learning from Inconsistent Decoder Features for Consistent Semi-supervised Medical Image Segmentation
This work addresses the challenge of data scarcity in medical image segmentation, offering a novel approach that outperforms existing methods, though it is incremental in the context of semi-supervised learning.
The paper tackles the problem of limited labeled data in volumetric medical image segmentation by proposing LeFeD, a semi-supervised learning method that learns from inconsistent decoder features to improve consistency, achieving state-of-the-art results on three public datasets.
Semi-supervised learning (SSL) has been proven beneficial for mitigating the issue of limited labeled data especially on the task of volumetric medical image segmentation. Unlike previous SSL methods which focus on exploring highly confident pseudo-labels or developing consistency regularization schemes, our empirical findings suggest that inconsistent decoder features emerge naturally when two decoders strive to generate consistent predictions. Based on the observation, we first analyze the treasure of discrepancy in learning towards consistency, under both pseudo-labeling and consistency regularization settings, and subsequently propose a novel SSL method called LeFeD, which learns the feature-level discrepancy obtained from two decoders, by feeding the discrepancy as a feedback signal to the encoder. The core design of LeFeD is to enlarge the difference by training differentiated decoders, and then learn from the inconsistent information iteratively. We evaluate LeFeD against eight state-of-the-art (SOTA) methods on three public datasets. Experiments show LeFeD surpasses competitors without any bells and whistles such as uncertainty estimation and strong constraints, as well as setting a new state-of-the-art for semi-supervised medical image segmentation. Code is available at \textcolor{cyan}{https://github.com/maxwell0027/LeFeD}