Abstract
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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Allan, J., Carbonell, J., Doddington, G., Yamron, J., Yang, Y.: Topic Detection and Tracking Pilot Study. Topic Detection and Tracking Workshop Report (2001)
Bayer, J., Münch, D., Arens, M.: Viewpoint Independency for Skeleton Based Human Action Recognition. Tech. rep, Fraunhofer IOSB, Ettlingen (2020)
Bhosale, S.V.: Holy Grail of Outlier Detection Technique: A Macro Level Take on the State of the Art. IJCSIT (2014)
Bishop, C.M.: Novelty detection and neural network validation. IEE Proc. Vision Image Signal Process. 141(4), 217–222 (1994)
Blender Online Community: Blender - a 3D modelling and rendering package (2019)
Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2D pose estimation using part affinity fields. In: CVPR 2017-Janua, pp. 1302–1310 (2017)
Carnegie Mellon Graphics Lab: CMU Graphics Lab Motion Capture Database
Chandola, V., Banerjee, A., Kumar, V.: Anomaly detection. ACM Comput. Surv. 41(3), 1–58 (2009)
Dasgupta, D., Forrest, S.: Novelty detection in time series data using ideas from immunology. In: The 8th International Conference on Intelligent Systems, pp. 82–87 (1999)
Devanne, M., Wannous, H., Berretti, S., Pala, P., Daoudi, M., Del Bimbo, A.: 3-D human action recognition by shape analysis of motion trajectories on riemannian manifold. IEEE Trans. Cybern. 45(7), 1340–1352 (2015)
DeVries, T., Taylor, G.W.: Learning confidence for out-of-distribution detection in neural networks. arXiv preprint arXiv:1802.04865 (2018)
Du, Y., Wang, W., Wang, L.: Hierarchical recurrent neural network for skeleton based action recognition. In: CVPR (2015)
Ester, M., Kriegel, H.P., Sander, J., Xu, X.: Others: a density-based algorithm for discovering clusters in large spatial databases with noise. KDD 96, 226–231 (1996)
John, G.H.: Robust decision trees: removing outliers from databases. In: KDD, pp. 174–179 (1995)
Garcia-Garcia, A., Orts-Escolano, S., Oprea, S., Villena-Martinez, V., Martinez-Gonzalez, P., Garcia-Rodriguez, J.: A survey on deep learning techniques for image and video semantic segmentation. Appl. Soft Comput. J. 70, 41–65 (2018)
Grubbs, F.E.: Procedures for detecting outlying observations in samples. Technometrics 11(1), 1–21 (1969)
Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: CVPR, vol. 2, pp. 1735–1742. IEEE (2006)
Hendrycks, D., Gimpel, K.: A baseline for detecting misclassified and out-of-distribution examples in neural networks. In: ICLR (2017)
Hilsenbeck, B., Münch, D., Kieritz, H., Hübner, W., Arens, M.: Hierarchical hough forests for view-independent action recognition. In: 2016 23rd International Conference on Pattern Recognition (ICPR), pp. 1911–1916 (2016)
Hinton, G., Vinyals, O., Dean, J.: Distilling the Knowledge in a Neural Network. arXiv preprint arXiv:1503.02531 (2015)
Hodge, V.J., Austin, J.: A survey of outlier detection methodologies. Artif. Intell. Rev. 22(2), 85–126 (2004)
Laurikkala, J., Juhola, M., Kentala, E.: Informal identification of outliers in medical data. In: IDAMAP, vol. 1, pp. 20–24 (2000)
Japkowicz, N., Myers, C., Gluck, M.: A novelty detection approach to classification. In: IJCAI, pp. 518–523, Montreal (1995)
Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: CVPR (2019)
Kerola, T., Inoue, N., Shinoda, K.: Spectral graph skeletons for 3D action recognition. In: Cremers, D., Reid, I., Saito, H., Yang, M.-H. (eds.) ACCV 2014. LNCS, vol. 9006, pp. 417–432. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-16817-3_27
Kliger, M., Fleishman, S.: Novelty Detection with GAN. arXiv preprint arXiv:1802.10560 (2018)
Knox, E.M., Ng, R.T.: Algorithms for mining distance based outliers in large datasets. In: VLDB, pp. 392–403. Citeseer (1998)
Kong, Y., Fu, Y.: Human action recognition and prediction: a survey. arXiv preprint arXiv:1806.11230 (2018)
Liang, S., Li, Y., Srikant, R.: Enhancing the reliability of out-of-distribution image detection in neural networks. In: ICLR (2018)
Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., Pietikäinen, M.: Deep learning for generic object detection: a survey. Int. J. Comput. Vision 128(2), 261–318 (2019). https://doi.org/10.1007/s11263-019-01247-4
Masana, M., Ruiz, I., Serrat, J., van de Weijer, J., Lopez, A.M.: Metric learning for novelty and anomaly detection. In: BMVC (2018)
Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483–499. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46484-8_29
Nguyen, A., Yosinski, J., Clune, J.: Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In: CVPR, pp. 427–436 (2015)
Papadopoulos, G.T., Axenopoulos, A., Daras, P.: Real-time skeleton-tracking-based human action recognition using kinect data. In: Gurrin, C., Hopfgartner, F., Hurst, W., Johansen, H., Lee, H., O’Connor, N. (eds.) MMM 2014. LNCS, vol. 8325, pp. 473–483. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-04114-8_40
Papandreou, G., Zhu, T., Chen, L.-C., Gidaris, S., Tompson, J., Murphy, K.: PersonLab: person pose estimation and instance segmentation with a bottom-up, part-based, geometric embedding model. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision – ECCV 2018. LNCS, vol. 11218, pp. 282–299. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01264-9_17
Pidhorskyi, S., Adjeroh, D.A., Doretto, G.: Adversarial latent autoencoders. In: CVPR (2020)
Poppe, R.: A survey on vision-based human action recognition. Image Vis. Comput. 28(6), 976–990 (2010)
Seheult, A.H., Green, P.J., Rousseeuw, P.J., Leroy, A.M.: Robust regression and outlier detection. J. Royal Stat. Soc. Ser. A (Stat. Soc.) 152(1), 133 (1989)
Shahroudy, A., Liu, J., Ng, T.T., Wang, G.: Ntu rgb+d: a large scale dataset for 3d human activity analysis. In: CVPR (2016)
Si, C., Jing, Y., Wang, W., Wang, L., Tan, T.: Skeleton-based action recognition with spatial reasoning and temporal stack learning. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 106–121. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01246-5_7
Szegedy, C., et al.: Intriguing properties of neural networks. In: ICLR (2014)
Tax, D., Ypma, A., Duin, R.: Support vector data description applied to machine vibration analysis. In: Proceedings of 5th Annual Conference of the Advanced School for Computing and Imaging, pp. 15–23 (1999)
The MakeHuman team: MakeHuman. www.makehumancommunity.org. Accessed 15 Nov 2020
Turaga, P., Chellappa, R., Subrahmanian, V.S., Udrea, O.: Machine recognition of human activities: A survey. TCSVT 18(11), 1473–1488 (2008)
Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: AAAI, pp. 7444–7452 (2018)
Zhao, M., et al.: Through-wall human pose estimation using radio signals. In: CVPR (2018)
Zimek, A., Filzmoser, P.: There and back again: outlier detection between statistical reasoning and data mining algorithms (2018)
Acknowledgements
This work was developed in Fraunhofer Cluster of Excellence “Cognitive Internet Technologies”.
Portions of the research in this paper used the NTU-RGB+D Action Recognition Dataset made available by the ROSE Lab at the Nanyang Technological University, Singapore.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Bayer, J., Münch, D., Arens, M. (2021). Image-Based Out-of-Distribution-Detector Principles on Graph-Based Input Data in Human Action Recognition. In: Del Bimbo, A., et al. Pattern Recognition. ICPR International Workshops and Challenges. ICPR 2021. Lecture Notes in Computer Science(), vol 12661. Springer, Cham. https://doi.org/10.1007/978-3-030-68763-2_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-68763-2_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-68762-5
Online ISBN: 978-3-030-68763-2
eBook Packages: Computer ScienceComputer Science (R0)