iUNets：具有可学习上采样和下采样的完全可逆U型网
iUNets: Fully invertible U-Nets with Learnable Up- and Downsampling
摘要：
U-Nets已经被建立为图像到图像学习问题的标准架构，例如成像中的分割和逆问题。对于大规模数据，例如出现在3D医学成像中的数据，U-Net具有过高的内存要求。在这里，我们提出了一种新的完全可逆的基于U-Net的架构，称为iUNet，它采用了新颖的可学习和可逆的上采样和下采样操作，从而使使用内存高效的反向传播成为可能。这使我们能够在相同的GPU内存限制下，在实践中训练更深、更大的网络。由于其可逆性，iUNet还可以用于构建规范化流。
英文摘要：
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. Due to its invertibility, the iUNet can furthermore be used for constructing normalizing flows.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
