-
Chapter and Conference Paper
Decoupled Consistency for Semi-supervised Medical Image Segmentation
By fully utilizing unlabeled data, the semi-supervised learning (SSL) technique has recently produced promising results in the segmentation of medical images. Pseudo labeling and consistency regularization are...
-
Chapter and Conference Paper
Research on Diabetic Retinal Fundus Screening Model Based on Conditional Generative Adversarial Nets
Retinal fundus screening is of great significance to the diagnosis of diabetes. However, the existing methods have various problems in retinal blood vessel segmentation and exudate detection, such as insuffici...
-
Chapter and Conference Paper
Community Detection Model Based on Graph Representation and Self-supervised Learning
Community detection is an important issue of social network analysis, which is used to find the potential connections between individuals. At present, the mainstream community detection methods consider using ...