Semantic Segmentation
/sɪˈmæntɪk ˌsɛɡmɛnˈteɪʃən/
A computer vision task that assigns a class label to every pixel in an image.
Semantic segmentation creates dense predictions, useful for understanding scene layout. Common architectures include U-Net, DeepLab, and Mask R-CNN for instance segmentation.
Examples
- Medical image segmentation
- Autonomous driving scene understanding
- Satellite image analysis