arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.01719cs.CVcs.LGeess.IV
收藏

基于图像的OoD-Detector人体动作识别中基于图的输入数据原理

Image-based OoD-Detector Principles on Graph-based Input Data in Human Action Recognition

Fraunhofer Center for Machine Learning(弗劳恩霍夫机器学习中心);Fraunhofer IOSB(弗劳恩霍夫IOSB研究所)

Jens Bayer, David Münch, Michael Arens

摘要:

生活在像我们这样的复杂世界中,机器学习系统的实际实现假设一个封闭的世界是不可接受的。因此,对于现实世界环境中的这种基于学习的系统来说,有必要意识到其自身的能力和限制,并且能够区分推断的置信和不置信结果,特别是如果样本不能由潜在分布解释。这些知识在安全关键环境和任务中尤其重要,例如自动驾驶汽车或医疗应用。为此,我们将基于图像的分布(OoD)方法转移到基于图形的数据,并显示其在动作识别中的适用性。这项工作的贡献是(i)检查最近的基于图像的OoD检测器的可移植性,基于图形的输入数据,(ii)基于度量学习的方法来检测OoD样本,以及(iii)引入一种新的半合成动作识别数据集。评估表明,基于图像的OoD方法可以应用于基于图形的数据。此外,在类内和数据集内结果的性能之间存在差距。第一种方法作为检查基线或ODIN提供合理的结果。与基于图像的应用相比,更复杂的网络架构在数据集内比较中被超越,甚至导致分类精度降低。

英文摘要:

Living in a complex world like ours makes it unacceptable that a practical implementation of a machine learning system assumes a closed world. Therefore, it is necessary for such a learning-based system in a real world environment, to be aware of its own capabilities and limits and to be able to distinguish between confident and unconfident results of the inference, especially if the sample cannot be explained by the underlying distribution. This knowledge is particularly essential in safety-critical environments and tasks e.g. self-driving cars or medical applications. Towards this end, we transfer image-based Out-of-Distribution (OoD)-methods to graph-based data and show the applicability in action recognition. The contribution of this work is (i) the examination of the portability of recent image-based OoD-detectors for graph-based input data, (ii) a Metric Learning-based approach to detect OoD-samples, and (iii) the introduction of a novel semi-synthetic action recognition dataset. The evaluation shows that image-based OoD-methods can be applied to graph-based data. Additionally, there is a gap between the performance on intraclass and intradataset results. First methods as the examined baseline or ODIN provide reasonable results. More sophisticated network architectures - in contrast to their image-based application - were surpassed in the intradataset comparison and even lead to less classification accuracy.

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。

↑