2025
Keep Your Friends Close, and Your Enemies Farther: Distance-aware Voxel-wise Contrastive Learning for Semi-supervised Multi-organ Segmentation
ICCV 2025poster
Based on pseudo-labels, voxel-wise contrastive learning (VCL) is a prominent approach designed to learn effective feature representations for semi-supervised medical image segmentation. However, in multi-organ segmentation (MoS), the complex anatomical structures of certain organs often lead to many…