Semi-Supervised Semantic Segmentation via Derivative Label Propagation
By: Yuanbin Fu, Xiaojie Guo
Potential Business Impact:
Improves computer vision accuracy with fewer labeled images.
Semi-supervised semantic segmentation, which leverages a limited set of labeled images, helps to relieve the heavy annotation burden. While pseudo-labeling strategies yield promising results, there is still room for enhancing the reliability of pseudo-labels. Hence, we develop a semi-supervised framework, namely DerProp, equipped with a novel derivative label propagation to rectify imperfect pseudo-labels. Our label propagation method imposes discrete derivative operations on pixel-wise feature vectors as additional regularization, thereby generating strictly regularized similarity metrics. Doing so effectively alleviates the ill-posed problem that identical similarities correspond to different features, through constraining the solution space. Extensive experiments are conducted to verify the rationality of our design, and demonstrate our superiority over other methods. Codes are available at https://github.com/ForawardStar/DerProp/.
Similar Papers
Boosting Generic Semi-Supervised Medical Image Segmentation via Diverse Teaching and Label Propagation
CV and Pattern Recognition
Helps doctors see inside bodies better with less training data.
Enhancing Dual Network Based Semi-Supervised Medical Image Segmentation with Uncertainty-Guided Pseudo-Labeling
CV and Pattern Recognition
Helps doctors find diseases with fewer scans.
Semi-Supervised Biomedical Image Segmentation via Diffusion Models and Teacher-Student Co-Training
CV and Pattern Recognition
Helps doctors find sickness in scans with less data.