CAKES：用于高效3D网络的逐层自动核收缩
CAKES: Channel-wise Automatic KErnel Shrinking for Efficient 3D Networks
摘要：
三维卷积神经网络（CNN）在三维场景理解中有着广泛的应用，如视频分析、体图像识别等。然而，3D网络很容易导致过度参数化，从而导致昂贵的计算成本。在本文中，我们提出了逐层自动内核收缩（CAKES），通过将标准3D卷积收缩为一组经济操作来实现高效的3D学习，例如，一维，二维卷积。与以前的方法不同，CAKES执行通道方式的内核收缩，其具有以下优点：1）使部署在每一层中的操作都是异构的，因此它们可以提取多样化和互补的信息，以利于学习过程; 2）允许有效和灵活的替换设计，可以推广到时空和体积数据。此外，我们提出了一个新的搜索空间基于CAKES，使更换配置可以自动确定简化的三维网络。CAKES显示出优于其他方法的性能，具有类似的模型大小，它也实现了相当的性能，以更少的参数和计算成本的任务，包括3D医学成像分割和视频动作识别的最先进的。代码和型号可在https://github.com/yucornetto/CAKES上获得
英文摘要：
3D Convolution Neural Networks (CNNs) have been widely applied to 3D scene understanding, such as video analysis and volumetric image recognition. However, 3D networks can easily lead to over-parameterization which incurs expensive computation cost. In this paper, we propose Channel-wise Automatic KErnel Shrinking (CAKES), to enable efficient 3D learning by shrinking standard 3D convolutions into a set of economic operations e.g., 1D, 2D convolutions. Unlike previous methods, CAKES performs channel-wise kernel shrinkage, which enjoys the following benefits: 1) enabling operations deployed in every layer to be heterogeneous, so that they can extract diverse and complementary information to benefit the learning process; and 2) allowing for an efficient and flexible replacement design, which can be generalized to both spatial-temporal and volumetric data. Further, we propose a new search space based on CAKES, so that the replacement configuration can be determined automatically for simplifying 3D networks. CAKES shows superior performance to other methods with similar model size, and it also achieves comparable performance to state-of-the-art with much fewer parameters and computational costs on tasks including 3D medical imaging segmentation and video action recognition. Codes and models are available at https://github.com/yucornetto/CAKES
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。
