Skip to main content
. 2026 Jan 9;5:1733003. doi: 10.3389/fradi.2025.1733003

Figure 1.

Flowchart of deep learning-based segmentation algorithms. It categorizes into three types: Semantic Segmentation, Instance Segmentation, and Panoptic Segmentation. Semantic Segmentation includes methods like CNN + CRF, FCN (VGG16), U-Net, and DeepLab V3. Instance Segmentation features DeepMask, Instance-Aware, Mask R-CNN, and CenterMask. Panoptic Segmentation involves Panoptic FPN, DetectoRS, UPS-Net, and Panoptic Deeplab.

Deep learning-based segmentation algorithm. Three algorithms of the segmentation, semantic instance, and panoptic are included.