Chapter 7

Segmentation

Segmentation assigns a class label to every pixel in an image — the most spatially precise of the standard CV tasks. This chapter distinguishes semantic from instance segmentation, explains the encoder-decoder design of U-Net and why skip connections are essential for spatial precision, and surveys the broader segmentation landscape including Mask R-CNN, DeepLabV3, and PSPNet.

• 1. Semantic v. Instance Segmentation→
• 2. U-Net→
• 3. Other Segmentation Architectures→