Cross-Domain Self-supervised Multi-task Feature Learning using Synthetic Imagery

Abstract

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.

References in corpus (8)

• Unsupervised Domain Adaptation by Backpropagation
• Adversarial Discriminative Domain Adaptation
• Places: An Image Database for Deep Scene Understanding
• Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning
• Playing for Data: Ground Truth from Computer Games
• R-CNNs for Pose Estimation and Action Detection
• PixelNet: Representation of the pixels, by the pixels, and for the pixels
• Semantic Scene Completion from a Single Depth Image