We introduce a novel principle for self-supervised feature learning based on
the discrimination of specific transformations of an image. We argue that the
generalization capability of learned features depends on what image
neighborhood size is sufficient to discriminate different image
transformations: The larger the required neighborhood size and the more global
the image statistics that the feature can describe. An accurate description of
global image statistics allows to better represent the shape and configuration
of objects and their context, which ultimately generalizes better to new tasks
such as object classification and detection. This suggests a criterion to
choose and design image transformations. Based on this criterion, we introduce
a novel image transformation that we call limited context inpainting (LCI).
This transformation inpaints an image patch conditioned only on a small
rectangular pixel boundary (the limited context). Because of the limited
boundary information, the inpainter can learn to match local pixel statistics,
but is unlikely to match the global statistics of the image. We claim that the
same principle can be used to justify the performance of transformations such
as image rotations and warping. Indeed, we demonstrate experimentally that
learning to discriminate transformations such as LCI, image warping and
rotations, yields features with state of the art generalization capabilities on
several datasets such as Pascal VOC, STL-10, CelebA, and ImageNet. Remarkably,
our trained features achieve a performance on Places on par with features
trained through supervised learning with ImageNet labels.

基于对特定变换的区分，我们提出了一种自监督特征学习的新原则，指出所学特征的泛化能力取决于较大的图像邻域大小和其能够描述的更全局的图像统计信息，这可以 better represent objects' shape and configuration 以及它们的上下文，最终将泛化到新任务，如对象分类和检测。根据这个标准，我们引入了一种新的图像变换，称为 limited context inpainting (LCI)，它仅在小矩形像素边界（有限的上下文）的条件下填充图像，而由于边界信息有限，因此涂鸦者可以学习匹配局部像素统计信息，但不太可能匹配图像的全局统计信息。我们声称可以使用同样的原则来验证变换性能，例如图像旋转和扭曲， 确实，我们实验表明，学习区分 LCI、图像扭曲和旋转等变换，产生了状态良好的泛化功能，可应用于多个数据集，如 Pascal VOC、STL-10、CelebA 和 ImageNet。值得注意的是，我们训练的特征在 Places 数据集上的表现与通过带 ImageNet 标签的监督学习训练的特征相当。