Cross-Domain Self-supervised Multi-task Feature Learning using Synthetic Imagery
This addresses the challenge of multi-task feature learning for computer vision researchers, though it is incremental as it builds on existing domain adaptation and multi-task methods.
The paper tackles the problem of learning generalizable visual representations by proposing a multi-task deep network trained on synthetic images with domain adaptation, achieving state-of-the-art transfer learning results on PASCAL VOC 2007 classification and 2012 detection.
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.