论文标题
打破对称性：在模棱两可的神经网络中解决对称性歧义
Breaking the Symmetry: Resolving Symmetry Ambiguities in Equivariant Neural Networks
论文作者
论文摘要
在许多3D学习领域都采用了模棱两可的网络。在这里，我们确定了这些网络的基本局限性：它们对对称性的歧义。模棱两可的网络无法完成与对称性有关的任务，例如将左右对称对象分割到其左侧和右侧。我们通过添加可以解决对称性歧义的组件，同时保留旋转模糊性来解决这个问题。我们提出OAVNN：方向意识到向量神经元网络，这是向量神经元网络的扩展。 Oavnn是一个旋转模棱两可的网络，对平面对称输入非常强大。我们的网络由三个关键组成部分组成。 1）我们引入了一种算法来计算对称性检测特征。 2）我们创建一个对称敏感的方向意识到线性层。 3）我们构建了一种关注机制，该机制将方向信息跨点关联。我们使用左右分段评估网络，发现网络很快获得了准确的分割。我们希望这项工作促使对对称对象的e夫网络的表现性进行调查。
Equivariant networks have been adopted in many 3-D learning areas. Here we identify a fundamental limitation of these networks: their ambiguity to symmetries. Equivariant networks cannot complete symmetry-dependent tasks like segmenting a left-right symmetric object into its left and right sides. We tackle this problem by adding components that resolve symmetry ambiguities while preserving rotational equivariance. We present OAVNN: Orientation Aware Vector Neuron Network, an extension of the Vector Neuron Network. OAVNN is a rotation equivariant network that is robust to planar symmetric inputs. Our network consists of three key components. 1) We introduce an algorithm to calculate symmetry detecting features. 2) We create a symmetry-sensitive orientation aware linear layer. 3) We construct an attention mechanism that relates directional information across points. We evaluate the network using left-right segmentation and find that the network quickly obtains accurate segmentations. We hope this work motivates investigations on the expressivity of equivariant networks on symmetric objects.
