Efficient Active Online Learning for 3D Reconstruction and Scene Understanding

用于 3D 重建和场景理解的高效主动在线学习

• 批准号: 260350367
• 负责人: Professor Dr. Daniel Cremers
• 金额: --
• 依托单位: Lehrstuhl für Informatik IX: Bildverarbeitung und Künstliche Intelligenz
• 依托单位国家: 德国
• 项目类别: Priority Programmes
• 财政年份: 2014
• 资助国家: 德国
• 起止时间: 2013-12-31 至 2020-12-31
• 项目状态: 已结题
• 来源: https://gepris.dfg.de/gepris/projekt/260350367?language=en
• 关键词: Efficient; Active; Online; Learning; 3D

Machine learning algorithms have become an important building block in modern computer vision systems. However, most of these systems are based on offline learning, i.e. learning is done only once before system deployment, and future adaptations to unobserved circumstances are not considered. Furthermore, the amount of labeled training data required for the learning task is usually very high, because the system has no possibility to select subsets of the training data that are particularly suited for the required classification task. Quite in contrast, human perception strongly relies on our capacity to constantly learn and adapt our acquired knowledge to new environments and circumstances. The goal of this project is to address this challenge by developing novel learning methods that perform the learning task with a higher degree of autonomy than current state-of-the-art systems. Here, autonomy refers to the ability of the system to decide which kind of information is more useful for more efficient learning. To achieve this, we will develop an Active Learning system, in which learning is done in cycles: After an initial training phase the system is presented with new observations for classification. Among them it selects those that are most infomative. For these, labels are queried from a human and the so obtained labeled data are used in the next round of training. This will lead to two major improvements over current systems: first, the required amount of labeled training data will be significantly lower, because the used training data will be much more context-oriented. And second, the system will have a much higher capability to adapt to new situations or environments, because learning is done in an ongoing process. Our Active Learning system will be applied to two important research challenges in computer vision, namely 3D reconstruction and scene understanding, and the aim is to achieve substantial performance improvements in these areas using our proposed autonomous, i.e. in this case active learningapproach.

机器学习算法已成为现代计算机视觉系统的重要组成部分。然而，这些系统大多数都是基于离线学习，即在系统部署之前仅进行一次学习，并且不考虑未来对未观察到的情况的适应。此外，学习任务所需的标记训练数据量通常非常高，因为系统不可能选择特别适合所需分类任务的训练数据子集。相比之下，人类的感知强烈依赖于我们不断学习并使所获得的知识适应新环境和情况的能力。 该项目的目标是通过开发新颖的学习方法来应对这一挑战，这些方法比当前最先进的系统具有更高程度的自主性来执行学习任务。这里，自主性是指系统决定哪种信息对更有效的学习更有用的能力。为了实现这一目标，我们将开发一个主动学习系统，其中学习是循环进行的：在初始训练阶段之后，系统会收到新的观察结果以进行分类。其中它选择那些信息最丰富的。为此，从人类那里查询标签，并将如此获得的标签数据用于下一轮训练。这将导致对当前系统的两大改进：首先，所需的标记训练数据量将显着降低，因为使用的训练数据将更加面向上下文。其次，系统将具有更高的适应新情况或环境的能力，因为学习是在持续的过程中完成的。我们的主动学习系统将应用于计算机视觉中的两个重要研究挑战，即 3D 重建和场景理解，目的是使用我们提出的自主学习方法（即本例中的主动学习方法）在这些领域实现显着的性能改进。