.png){kind=icon}
.png){kind=icon}
Return
Adaptive Mix for Semi-Supervised Medical Image Segmentation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.media.2025.103857.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Existing mix-up methods for consistency regularization tend to generate perturbed images with uncontrollable, trivial, or overly strong perturbation intensity. • Uncontrollable mix-up limits the effectiveness of consistency regularization. • Mix-up operations with dynamically adjusted perturbation strength based on the segmentation model’s state can significantly enhance the effectiveness of consistency regularization. • Perturbation strategies are more important than learning paradigms for consistency regularization.
Journal
IF:
11.8
Papers:
3.8K
Citations:
2.4W