iUNets: Learnable Invertible Up- and Downsampling for Large-Scale Inverse Problems
Christian Etmann, Rihuan Ke, Carola‐Bibiane Schönlieb
Abstract
U-Nets have been established as a standard neural network architecture for image-to-image problems such as segmentation and inverse problems in imaging. For high-dimensional applications, as they for example appear in 3D medical imaging, U-Nets however have prohibitive memory requirements. Here, we present a new fully-invertible U-Net-based architecture called the iUNet, which allows for the application of highly memory-efficient backpropagation procedures. As its main building block, we introduce learnable and invertible up- an downsampling operations. For this, we developed an open-source implementation in Pytorch for 1D, 2D and 3D data.
Topics & Concepts
Invertible matrixUpsamplingComputer scienceBlock (permutation group theory)InverseTheoretical computer scienceBackpropagationArtificial intelligenceInverse problemArchitectureScale (ratio)Artificial neural networkAlgorithmImage (mathematics)MathematicsPure mathematicsGeometryPhysicsVisual artsMathematical analysisQuantum mechanicsArtBrain Tumor Detection and ClassificationAdvanced Neural Network ApplicationsMedical Imaging and Analysis