TL;DR研究多种自监督学习任务相结合的方法,用于训练单一的视觉表征,并在 ImageNet 分类、PASCAL VOC 检测和 NYU 深度预测上获得了优秀的结果。
Abstract
We investigate methods for combining multiple self-supervised tasks--i.e.,
supervised tasks where data can be collected without manual labeling--in order
to train a single visual representation. First, we provide