UNet is a widely adopted convolutional neural network architecture designed for semantic segmentation. Its U-shaped structure consists of a contracting path (downsampling) to capture context and an expansive path (upsampling) to recover spatial resolution, with skip connections that fuse low-level and high-level features. UNet is renowned for its accuracy in medical imaging (e.g., tumor segmentation) and satellite image analysis, setting a benchmark for segmentation tasks.
