Semantic segmentation: a label for every pixel
How semantic segmentation labels every pixel: fully convolutional networks (FCN), transposed convolutions, checkerboards, and dilated convolutions.
Part of Labelling every pixel.
Read first
- Convolutional neural networks (CNNs): filters, pooling
How convolutional neural networks (CNNs) learn small filters shared across an image, count their weights, pool, and stack layers, from LeNet to AlexNet and VGG.
Read next
- U-Net: skip connections for image segmentation
How the U-Net segments images: an encoder shrinks to see what is there, a decoder grows back, and skip connections copy fine detail across.