具有自适应多相上采样的真移位等变卷积神经网络
Truly shift-equivariant convolutional neural networks with adaptive polyphase upsampling
摘要：
卷积神经网络由于下采样层的存在而缺乏移位等方差。在图像分类中，最近提出了自适应多相下采样（APS-D），以使CNN具有完美的平移不变性。然而，在用于图像重建任务的网络中，它本身不能恢复移位等方差。我们通过提出自适应多相上采样（APS-U）来解决这个问题，APS-U是传统上采样的非线性扩展，它允许具有对称编码器-解码器架构（例如U-Net）的CNN表现出完美的移位等方差。通过MRI和CT重建实验，我们证明了包含APS-D/U层的网络在不牺牲图像重建质量的情况下表现出最先进的等方差性能。此外，与数据增强和抗混叠等现有方法不同，从APS-D/U获得的等方差增益还扩展到训练分布之外的图像。
英文摘要：
Convolutional neural networks lack shift equivariance due to the presence of downsampling layers. In image classification, adaptive polyphase downsampling (APS-D) was recently proposed to make CNNs perfectly shift invariant. However, in networks used for image reconstruction tasks, it can not by itself restore shift equivariance. We address this problem by proposing adaptive polyphase upsampling (APS-U), a non-linear extension of conventional upsampling, which allows CNNs with symmetric encoder-decoder architecture (for example U-Net) to exhibit perfect shift equivariance. With MRI and CT reconstruction experiments, we show that networks containing APS-D/U layers exhibit state of the art equivariance performance without sacrificing on image reconstruction quality. In addition, unlike prior methods like data augmentation and anti-aliasing, the gains in equivariance obtained from APS-D/U also extend to images outside the training distribution.
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。
