iUNets: Fully invertible U-Nets with Learnable Up- and Downsampling

Understand

U-Nets have been established as a standard architecture for image-to-image learning problems such as segmentation and inverse problems in imaging.

• For large-scale data, as it for example appears in 3D medical imaging, the U-Net however has prohibitive memory requirements.
• Here, we present a new fully-invertible U-Net-based architecture called the iUNet, which employs novel learnable and invertible up- and downsampling operations, thereby making the use of memory-efficient backpropagation possible.
• This allows us to train deeper and larger networks in practice, under the same GPU memory restrictions.