Understanding U-Net

U-Net has become the go-to method for image segmentation. But how did it come to be?

Table of content
1. The task at hand
2. Encoder-Decoder
3. Skip connections
4. Implementation details
a. Loss function
b. Up-sampling methods
c. To pad or not to pad?
5. U-Net in action

The task at hand

U-Net is developed for the task of semantic segmentation. When a neural network is fed images as inputs, we can choose …

computer vision deep learning machine learning segmentation self driving cars understanding