Abstract
Availability of labelled data is the major obstacle to the deployment of deep learning algorithms for computer vision tasks in new domains. The fact that many frameworks adopted to solve different tasks share the same architecture suggests that there should be a way of reusing the knowledge learned in a specific setting to solve novel tasks with limited or no additional supervision. In this work, we first show that such knowledge can be shared across tasks by learning a mapping between task-specific deep features in a given domain. Then, we show that this mapping function, implemented by a neural network, is able to generalize to novel unseen domains. Besides, we propose a set of strategies to constrain the learned feature spaces, to ease learning and increase the generalization capability of the mapping network, thereby considerably improving the final performance of our framework. Our proposal obtains compelling results in challenging synthetic-to-real adaptation scenarios by transferring knowledge between monocular depth estimation and semantic segmentation tasks.
Abstract (translated)
标记数据可用性是在新领域应用深度学习算法时所面临的主要障碍。许多框架解决不同任务共享相同的架构,这表明应该有一种方法来重用在特定的场景中学习的知识,以解决有限或没有额外监督的新颖任务。在本文中,我们首先表明,这种知识可以通过学习特定领域的任务特定的深特征之间的映射来共享。然后,我们表明,这个映射函数由神经网络实现,能够泛化到未曾见过的新领域。此外,我们提出了一组策略来限制学习的特征空间,减轻学习并增加映射网络的泛化能力,从而显著改善我们的框架的最终性能。我们的建议通过将单眼深度估计和语义分割任务的知识传递到合成到真实适应场景取得了令人信服的结果。
URL
https://arxiv.org/abs/2301.11310