本文的第一作者为陈智强，题目为：“Sharing Weights in Shallow Layers via Rotation Group Equivariant Convolutions”，发表于Machine Intelligence Research

以下为文章摘要：

Convolution operation possesses the characteristic of translation group equivariance. To achieve more group equivariances, Rotation Group Equivariant Convolutions(RGEC) is proposed to acquire both translation and rotation group equivariances. However, previous works paid more attention to the amount of parameters and usually ignored other resource costs. In this paper, we construct our networks without introducing extra resource costs. Specifically, a convolution kernel is rotated to different orientations for feature extractions of multiple channels, meanwhile, much fewer kernels than previous works are used to ensure that the output channel does not increase. To further enhance the orthogonality of kernels in different orientations, we construct the non-maximum-suppression loss on the rotation dimension to suppress the other directions except the most activated one. Considering that the low-level features benefit more from the rotational symmetry, we only Share Weights in the Shallow Layers (SWSL) via RGEC. Extensive experiments on multiple datasets (i.e., ImageNet, CIFAR, and MNIST) demonstrate that SWSL can effectively benefit from the higher-degree weight sharing and improve the performances of various networks including plain and ResNet architectures. Meanwhile, the convolutional kernels and parameters are much fewer (e.g., 75%, 87.5% fewer) in the shallow layers and no extra computation costs are introduced.

文章链接：https://link.springer.com/article/10.1007/s11633-022-1324-5