Transformation-robustness is an important feature for machine learning models that perform image classification. Many methods aim to bestow this property to models by the use of data augmentation strategies, while more formal guarantees are obtained via the use of equivariant models. We recognise that compositional, or part-whole structure is also an important aspect of images that has to be considered for building transformation-robust models. Thus, we propose a capsule network model that is, at once, equivariant and compositionality-aware. Equivariance of our capsule network model comes from the use of equivariant convolutions in a carefully-chosen novel architecture. The awareness of compositionality comes from the use of our proposed novel, iterative, graph-based routing algorithm, termed Iterative collaborative routing (ICR). ICR, the core of our contribution, weights the predictions made for capsules based on an iteratively averaged score of the degree-centralities of its nearest neighbours. Experiments on transformed image classification on FashionMNIST, CIFAR-10, and CIFAR-100 show that our model that uses ICR outperforms convolutional and capsule baselines to achieve state-of-the-art performance.
翻译:变形- 紫外线是进行图像分类的机器学习模型的一个重要特征。 许多方法的目的是通过使用数据增强战略将这种属性赋予模型,同时通过使用等同模型获得更正式的保障。 我们认识到,组成结构或半整体结构也是图像的一个重要方面,在建设变形- 紫外线模型时必须考虑的图像中也是如此。因此,我们提议一个胶囊网络模型,它同时具有等差性和成份性;我们胶囊网络模型的均匀性来自在精心选取的新结构中使用的静态相变组合。对组成性的认识来自我们拟议的新颖的、迭代的、基于图表的路线算法,称为迭代式合作路线(ICR)。 ICR是我们贡献的核心,是根据其近邻不同程度程度的迭代平均分数对胶囊所作的预测。实验来自对Fashion MNIST、CIFAR- 10和CIFAR- 100的图像转换分类的实验。 模型显示,我们使用ICRFRA- Contramal 的模模模范号,即ICRADRADRA- Contral。