论文标题
学习规范转换
Learning Canonical Transformations
论文作者
论文摘要
人类了解一组规范的几何变换（例如翻译和旋转），它们通过不受限制地限制到任何特定对象来支持概括。我们探索诱导性偏见，以帮助神经网络模型学习像素空间中的这些转换，以概括性域外的方式。具体而言，我们发现高训练集的多样性足以推断翻译到看不见的形状和尺度，并且迭代训练方案可以在时间上显着推断旋转。
Humans understand a set of canonical geometric transformations (such as translation and rotation) that support generalization by being untethered to any specific object. We explore inductive biases that help a neural network model learn these transformations in pixel space in a way that can generalize out-of-domain. Specifically, we find that high training set diversity is sufficient for the extrapolation of translation to unseen shapes and scales, and that an iterative training scheme achieves significant extrapolation of rotation in time.
