基于概率内省的几何稳定特征自监督学习
Self-supervised Learning of Geometrically Stable Features Through Probabilistic Introspection
摘要：
自我监督可以大大减少训练深度神经网络所需的手动标记数据量。虽然自我监督通常被认为是任务，如图像分类，在本文中，我们的目标是将其扩展到面向几何的任务，如语义匹配和部分检测。我们这样做的基础上，最近的几个想法，在无监督的地标检测。我们的方法学习密集独特的视觉描述符从一个未标记的图像数据集使用合成图像变换。它这样做的一个强大的概率公式，可以introductionally确定哪些图像区域可能会导致稳定的图像匹配的装置。我们的经验表明，以这种方式预训练的网络与许多预训练方案相比，需要更少的监督来学习语义对象部分。我们还表明，预先训练的表示是优秀的语义对象匹配。
英文摘要：
Self-supervision can dramatically cut back the amount of manually-labelled data required to train deep neural networks. While self-supervision has usually been considered for tasks such as image classification, in this paper we aim at extending it to geometry-oriented tasks such as semantic matching and part detection. We do so by building on several recent ideas in unsupervised landmark detection. Our approach learns dense distinctive visual descriptors from an unlabelled dataset of images using synthetic image transformations. It does so by means of a robust probabilistic formulation that can introspectively determine which image regions are likely to result in stable image matching. We show empirically that a network pre-trained in this manner requires significantly less supervision to learn semantic object parts compared to numerous pre-training alternatives. We also show that the pre-trained representation is excellent for semantic object matching.
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。
