About this document
088-Dynamic Contrastive Learning Guided by Class Confidence and Confusion Degree For Medical Image Segmentation by 729648zx is a document available to read on EtoBox.
This paper introduces a Dynamic Contrastive Learning framework for medical image segmentation that utilizes intra-Class-confidence and inter-Class-confusion to enhance pixel sampling strategies during training. The method dynamically selects expressive pixels for constructing positive and negative pairs based on the model
- Author
- 729648zx
- Language
- EN