Equivariance of neural networks to transformations helps to improve their performance and reduce generalization error in computer vision tasks, as they apply to datasets presenting symmetries (e.g. scalings, rotations, translations). The method of moving frames is classical for deriving operators invariant to the action of a Lie group in a manifold.Recently, a rotation and translation equivariant neural network for image data was proposed based on the moving frames approach. In this paper we significantly improve that approach by reducing the computation of moving frames to only one, at the input stage, instead of repeated computations at each layer. The equivariance of the resulting architecture is proved theoretically and we build a rotation and translation equivariant neural network to process volumes, i.e. signals on the 3D space. Our trained model overperforms the benchmarks in the medical volume classification of most of the tested datasets from MedMNIST3D.
翻译:神经网络对变的均匀性有助于改进其性能,减少计算机视觉任务中的一般错误,因为它们适用于显示对称(例如缩放、旋转、翻译)的数据集。移动框架的方法是典型的,用来推断操作者对立体组的动作变化。最近,根据移动框架方法,提出了图像数据旋转和翻译等异性神经网络的建议。在本文件中,我们大大改进了这一方法,将移动框架的计算方法在输入阶段只减少到一个,而不是在每一层重复计算。由此产生的结构的均匀性在理论上得到了证明,我们建立了一个用于处理体积的旋转和翻译等异性神经网络,即3D空间上的信号。我们经过培训的模型超越了MedMNDIST3D所测试的大多数数据集的医疗量分类基准。