arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1801.06397cs.CVstat.ML
收藏

什么是学习差异和光流估计的良好合成训练数据?

What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?

Technical University of Munich(慕尼黑工业大学);University of Freiburg(弗莱堡大学)

Nikolaus Mayer, Eddy Ilg, Philipp Fischer, Caner Hazirbas, Daniel Cremers, Alexey Dosovitskiy, Thomas Brox

摘要:

非常大的网络可以被有效和可靠地训练,这一发现导致了计算机视觉从工程解决方案到学习公式的范式转变。因此,研究的挑战从设计算法转向为监督学习创建合适且丰富的训练数据。如何高效地创建这样的训练数据?视觉识别中占主导地位的数据采集方法是基于Web数据和人工标注。然而,对于许多计算机视觉问题,例如立体或光流估计,这种方法是不可行的,因为人类无法手动进入像素精确的流场。在本文中,我们提倡使用综合生成的数据来训练深度网络,我们提出了多种方法来生成此类数据,并评估数据集属性对结果网络的性能和泛化属性的影响。我们还展示了在训练过程的选定阶段使用不同类型数据的学习计划的好处。

英文摘要:

The finding that very large networks can be trained efficiently and reliably has led to a paradigm shift in computer vision from engineered solutions to learning formulations. As a result, the research challenge shifts from devising algorithms to creating suitable and abundant training data for supervised learning. How to efficiently create such training data? The dominant data acquisition method in visual recognition is based on web data and manual annotation. Yet, for many computer vision problems, such as stereo or optical flow estimation, this approach is not feasible because humans cannot manually enter a pixel-accurate flow field. In this paper, we promote the use of synthetically generated data for the purpose of training deep networks on such tasks.We suggest multiple ways to generate such data and evaluate the influence of dataset properties on the performance and generalization properties of the resulting networks. We also demonstrate the benefit of learning schedules that use different types of data at selected stages of the training process.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑