In human learning, it is common to use multiple sources of information jointly. However, most existing feature learning approaches learn from only a single task. In this paper, we propose a novel multi-task deep network to learn generalizable high-level visual representations. Since multi-task learning requires annotations for multiple properties of the same training instance, we look to synthetic images to train our network. To overcome the domain difference between real and synthetic data, we employ an unsupervised feature space domain adaptation method based on adversarial learning. Given an input synthetic RGB image, our network simultaneously predicts its surface normal, depth, and instance contour, while also minimizing the feature space domain differences between real and synthetic data. Through extensive experiments, we demonstrate that our network learns more transferable representations compared to single-task baselines. Our learned representation produces state-of-the-art transfer learning results on PASCAL VOC 2007 classification and 2012 detection.

本文提出了一种多任务深度网络学习通用高级视觉表示的方法，并通过对人工制成的图像进行训练来克服真实与合成数据之间的领域差异，模型考虑同步从合成 RGB 图像中预测其表面法向、深度和实例轮廓，并最小化真实和合成数据之间特征空间的差异，在广泛实验的基础上，表明我们的网络相比单任务基线学习到更具有可转移性的表示，使得在 PASCAL VOC 2007 分类和 2012 检测上能够产生最先进的迁移学习结果。

跨域自监督多任务特征学习：使用合成图像