U-nets how exaclty is upsampling performed

1. How does upsampling work in U-Net?
2. How does upsampling work?
3. How is upsampling done in CNN?
4. Which of the following methods can be used for upsampling?

How does upsampling work in U-Net?

Transposed convolution is an upsampling technic that expands the size of images. There is a visualised demo here and an explanation here. Basically, it does some padding on the original image followed by a convolution operation.

How does upsampling work?

It works by repeating the rows and columns of the input. A more elaborate approach is to perform a backwards convolutional operation, originally referred to as a deconvolution, which is incorrect, but is more commonly referred to as a fractional convolutional layer or a transposed convolutional layer.

How is upsampling done in CNN?

In the Downsampling network, simple CNN architectures are used and abstract representations of the input image are produced. In the Upsampling network, the abstract image representations are upsampled using various techniques to make their spatial dimensions equal to the input image.

Which of the following methods can be used for upsampling?

Three deep-learning-based upsampling methods typically used in CNN. a Unpooling. b Transposed convolution. c Sub pixel convolution.