旋转蜘蛛和反射狗：学习数据增强分布的类条件方法
Rotating spiders and reflecting dogs: a class conditional approach to learning data augmentation distributions
摘要：
构建对无意义转换的不变性对于构建高效且可推广的机器学习模型至关重要。在实践中，学习不变性的最常见方法是通过数据增强。最近有兴趣的方法，学习分布的增广变换从训练数据本身的发展。虽然这种方法是有益的，因为它们响应于数据，但它们忽略了这样一个事实，即在许多情况下，模型需要不变的转换范围取决于特定的输入类。例如，如果一个模型需要能够预测图像中是海星还是狗，我们可能希望在训练过程中对海星图像应用随机旋转（因为它们没有首选方向），但我们不希望对狗的图像这样做。在这项工作中，我们介绍了一种方法，通过这种方法，我们可以学习类条件分布的增广变换。我们给出了一些例子，其中我们的方法根据类学习不同的无意义的变换，并进一步展示了我们的方法如何用作工具来探测潜在复杂数据集的固有对称性。
英文摘要：
Building invariance to non-meaningful transformations is essential to building efficient and generalizable machine learning models. In practice, the most common way to learn invariance is through data augmentation. There has been recent interest in the development of methods that learn distributions on augmentation transformations from the training data itself. While such approaches are beneficial since they are responsive to the data, they ignore the fact that in many situations the range of transformations to which a model needs to be invariant changes depending on the particular class input belongs to. For example, if a model needs to be able to predict whether an image contains a starfish or a dog, we may want to apply random rotations to starfish images during training (since these do not have a preferred orientation), but we would not want to do this to images of dogs. In this work we introduce a method by which we can learn class conditional distributions on augmentation transformations. We give a number of examples where our methods learn different non-meaningful transformations depending on class and further show how our method can be used as a tool to probe the symmetries intrinsic to a potentially complex dataset.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
