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
this https URL

本研究提出一种名为 CAKES 的自动核收缩的方法，通过将标准的 3D 卷积缩小为一组经济操作（例如 1D、2D 卷积），实现了高效的 3D 学习。与以往方法不同，CAKES 执行通道级核收缩，具有提取多样和互补信息以受益学习过程以及有效和灵活的替换设计等好处。并基于此提出了一种新的搜索空间，可以自动确定替换配置以简化 3D 网络。在 3D 医学成像分割和视频动作识别等任务上，CAKES 对于类似模型大小的其他方法显示了优越的性能，并且它也实现了与现有技术相当的性能，但具有更少的参数和计算成本。