Concept
U-Net
U-Net is a convolutional encoder-decoder architecture, named for the U shape of its diagram, originally built for biomedical image segmentation. Like a standard autoencoder, it downsamples an input to a compact bottleneck and then upsamples back to full resolution, except it…
The rest of “U-Net” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.
Log in to unlock→