论文标题
细心的集团模棱两可的卷积网络
Attentive Group Equivariant Convolutional Networks
论文作者
论文摘要
尽管小组卷积网络能够根据对称模式学习强大的表示，但它们缺乏了解它们之间有意义的关系的明确手段（例如，相对位置和姿势）。在本文中，我们介绍了对小组卷积的概括，在卷积过程中将注意力应用于强调有意义的对称组合并抑制不可行的，误导性的杂音。我们表明，先前的视觉注意力工作可以描述为我们提出的框架的特殊情况，并从经验上表明，我们的专注组模棱两可的卷积网络始终在基准图像数据集中始终优于常规组卷积网络。同时，我们通过可视化模棱两可的注意图为学习的概念提供了解释性。
Although group convolutional networks are able to learn powerful representations based on symmetry patterns, they lack explicit means to learn meaningful relationships among them (e.g., relative positions and poses). In this paper, we present attentive group equivariant convolutions, a generalization of the group convolution, in which attention is applied during the course of convolution to accentuate meaningful symmetry combinations and suppress non-plausible, misleading ones. We indicate that prior work on visual attention can be described as special cases of our proposed framework and show empirically that our attentive group equivariant convolutional networks consistently outperform conventional group convolutional networks on benchmark image datasets. Simultaneously, we provide interpretability to the learned concepts through the visualization of equivariant attention maps.
