arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.16867cs.CVcs.LG
收藏

利用几何先验知识提升深度神经网络:综述

Boosting Deep Neural Networks with Geometrical Prior Knowledge: A Survey

Robert Bosch GmbH(罗伯特·博世有限公司);University of Lübeck(吕贝克大学)

Matthias Rath, Alexandru Paul Condurache

摘要:

深度神经网络通过利用大量的训练数据,在许多不同的问题设置中获得最先进的结果。然而,收集、存储和--在监督学习的情况下--标记数据是昂贵和耗时的。此外,评估网络的泛化能力或预测在输入变换下推断的输出如何变化是复杂的,因为网络通常被视为黑盒。这两个问题都可以通过将先验知识结合到神经网络中来缓解。受卷积神经网络在计算机视觉任务中的成功启发,一种有前途的方法是结合关于问题的对称几何变换的知识来解决,以可预测的方式影响输出。这有望提高数据效率和更可解释的网络输出。在这篇综述中,我们试图对将几何先验知识引入神经网络的不同方法进行简要概述。此外,我们将这些方法与自动驾驶的3D目标检测相连接,我们希望在应用这些方法时获得有希望的结果。

英文摘要:

Deep Neural Networks achieve state-of-the-art results in many different problem settings by exploiting vast amounts of training data. However, collecting, storing and - in the case of supervised learning - labelling the data is expensive and time-consuming. Additionally, assessing the networks' generalization abilities or predicting how the inferred output changes under input transformations is complicated since the networks are usually treated as a black box. Both of these problems can be mitigated by incorporating prior knowledge into the neural network. One promising approach, inspired by the success of convolutional neural networks in computer vision tasks, is to incorporate knowledge about symmetric geometrical transformations of the problem to solve that affect the output in a predictable way. This promises an increased data efficiency and more interpretable network outputs. In this survey, we try to give a concise overview about different approaches that incorporate geometrical prior knowledge into neural networks. Additionally, we connect those methods to 3D object detection for autonomous driving, where we expect promising results when applying those methods.

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。

↑