Search papers, labs, and topics across Lattice.
SAUF-Net addresses the challenges of semi-supervised medical image segmentation by introducing a Structure--Appearance Decomposition Module (SADM) that separates structural and appearance features, enhancing the reliability of pseudo labels. The model incorporates a Disentangled Guidance Module (DGM) to improve segmentation accuracy and an Auxiliary Decoder for reliability estimation, which collectively mitigate error accumulation from unstable appearance variations. Extensive experiments on ISIC-2016 and Kvasir-SEG show that SAUF-Net significantly outperforms existing semi-supervised methods, particularly in low-label scenarios, highlighting its effectiveness in medical applications.
Unstable appearance variations can lead to unreliable pseudo labels, but SAUF-Net's innovative structure-aware approach dramatically enhances segmentation accuracy in low-label settings.
Semi-supervised learning has shown great potential for reducing annotation costs in medical image segmentation. However, most existing methods mainly exploit unlabeled data through prediction-level consistency, while the reliability of internal feature representations is often overlooked. In medical images, target-related structural cues are easily entangled with unstable appearance variations, which may lead to unreliable pseudo labels and error accumulation during training. To address these issues, we propose SAUF-Net, a Structure--Appearance Representation Learning with Uncertainty Feedback Network for semi-supervised medical image segmentation. SAUF-Net uses the Structure--Appearance Decomposition Module (SADM) to separate bottleneck features into structural and appearance representations. The Disentangled Guidance Module (DGM) injects these representations into the decoding process to enhance structure-aware segmentation. Meanwhile, the Auxiliary Decoder produces branch-specific predictions for reliability estimation and a fused prediction for appearance-swapped consistency. Furthermore, we introduce an Appearance-Swapped Consistency branch to encourage structural representations to remain stable under appearance variations. We also introduce a reliability-map-guided dual-head discriminator with a Validity Head and an Uncertainty Head to provide feature-level uncertainty feedback. Extensive experiments on ISIC-2016 and Kvasir-SEG demonstrate that SAUF-Net outperforms state-of-the-art semi-supervised methods, especially under low-label settings.
