Skip to main content
Fachgebiete
Automobil + Motoren Bauwesen + Immobilien Business IT + Informatik Elektrotechnik + Elektronik Energie + Nachhaltigkeit Finance + Banking Management + Führung Marketing + Vertrieb Maschinenbau + Werkstoffe Versicherung + Risiko
DE
EN
Bücher
Zeitschriften
Themenseiten
Organisationspsychologie Projektmanagement Marketing Smart Manufacturing
Weitere Formate
Podcasts Webinare Technik Webinare Wirtschaft Kongresse Veranstaltungskalender Awards
Jetzt Einzelzugang starten
Zugang für Unternehmen
Referenzkunden
SLX-Digitalkonferenz: Zukunftswerkstatt 2024

Mehr Umsatz mit Top-Kontakten

Am 7. Mai erfahren Sie, wie Vertriebsteams Leadgenerierung, Leadnurturing und Leadstrategien effizient steuern können.
Erweiterte Suche
Anmelden
nach oben
Erschienen in:
Subject Identification Across Large Expression Variations Using 3D Facial Landmarks Kapitel lesen Erstes Kapitel lesen

2021 | OriginalPaper | Buchkapitel

Image-Based Out-of-Distribution-Detector Principles on Graph-Based Input Data in Human Action Recognition

verfasst von : Jens Bayer, David Münch, Michael Arens

Erschienen in: Pattern Recognition. ICPR International Workshops and Challenges

Verlag: Springer International Publishing

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

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.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Jetzt informieren
Vorheriges Kapitel 3D Human Pose Estimation Based on Multi-Input Multi-Output Convolutional Neural Network and Event Cameras: A Proof of Concept on the DHP19 Dataset
Nächstes Kapitel A Novel Joint Points and Silhouette-Based Method to Estimate 3D Human Pose and Shape
Literatur
1.
Allan, J., Carbonell, J., Doddington, G., Yamron, J., Yang, Y.: Topic Detection and Tracking Pilot Study. Topic Detection and Tracking Workshop Report (2001)
2.
Bayer, J., Münch, D., Arens, M.: Viewpoint Independency for Skeleton Based Human Action Recognition. Tech. rep, Fraunhofer IOSB, Ettlingen (2020)
3.
Bhosale, S.V.: Holy Grail of Outlier Detection Technique: A Macro Level Take on the State of the Art. IJCSIT (2014)
4.
Bishop, C.M.: Novelty detection and neural network validation. IEE Proc. Vision Image Signal Process. 141(4), 217–222 (1994)CrossRef
5.
Blender Online Community: Blender - a 3D modelling and rendering package (2019)
6.
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)
7.
Carnegie Mellon Graphics Lab: CMU Graphics Lab Motion Capture Database
8.
Chandola, V., Banerjee, A., Kumar, V.: Anomaly detection. ACM Comput. Surv. 41(3), 1–58 (2009)CrossRef
9.
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)
10.
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)CrossRef
11.
DeVries, T., Taylor, G.W.: Learning confidence for out-of-distribution detection in neural networks. arXiv preprint arXiv:​1802.​04865 (2018)
12.
Du, Y., Wang, W., Wang, L.: Hierarchical recurrent neural network for skeleton based action recognition. In: CVPR (2015)
13.
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)
14.
John, G.H.: Robust decision trees: removing outliers from databases. In: KDD, pp. 174–179 (1995)
15.
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)
16.
Grubbs, F.E.: Procedures for detecting outlying observations in samples. Technometrics 11(1), 1–21 (1969)CrossRef
17.
Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: CVPR, vol. 2, pp. 1735–1742. IEEE (2006)
18.
Hendrycks, D., Gimpel, K.: A baseline for detecting misclassified and out-of-distribution examples in neural networks. In: ICLR (2017)
19.
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)
20.
21.
Hodge, V.J., Austin, J.: A survey of outlier detection methodologies. Artif. Intell. Rev. 22(2), 85–126 (2004)CrossRef
22.
Laurikkala, J., Juhola, M., Kentala, E.: Informal identification of outliers in medical data. In: IDAMAP, vol. 1, pp. 20–24 (2000)
23.
Japkowicz, N., Myers, C., Gluck, M.: A novelty detection approach to classification. In: IJCAI, pp. 518–523, Montreal (1995)
24.
Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: CVPR (2019)
25.
26.
27.
Knox, E.M., Ng, R.T.: Algorithms for mining distance based outliers in large datasets. In: VLDB, pp. 392–403. Citeseer (1998)
28.
29.
Liang, S., Li, Y., Srikant, R.: Enhancing the reliability of out-of-distribution image detection in neural networks. In: ICLR (2018)
30.
31.
Masana, M., Ruiz, I., Serrat, J., van de Weijer, J., Lopez, A.M.: Metric learning for novelty and anomaly detection. In: BMVC (2018)
32.
33.
Nguyen, A., Yosinski, J., Clune, J.: Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In: CVPR, pp. 427–436 (2015)
34.
35.
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_​17CrossRef
36.
Pidhorskyi, S., Adjeroh, D.A., Doretto, G.: Adversarial latent autoencoders. In: CVPR (2020)
37.
Poppe, R.: A survey on vision-based human action recognition. Image Vis. Comput. 28(6), 976–990 (2010)CrossRef
38.
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)
39.
Shahroudy, A., Liu, J., Ng, T.T., Wang, G.: Ntu rgb+d: a large scale dataset for 3d human activity analysis. In: CVPR (2016)
40.
41.
Szegedy, C., et al.: Intriguing properties of neural networks. In: ICLR (2014)
42.
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)
43.
44.
Turaga, P., Chellappa, R., Subrahmanian, V.S., Udrea, O.: Machine recognition of human activities: A survey. TCSVT 18(11), 1473–1488 (2008)
45.
Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: AAAI, pp. 7444–7452 (2018)
46.
Zhao, M., et al.: Through-wall human pose estimation using radio signals. In: CVPR (2018)
47.
Zimek, A., Filzmoser, P.: There and back again: outlier detection between statistical reasoning and data mining algorithms (2018)
Metadaten
Titel
Image-Based Out-of-Distribution-Detector Principles on Graph-Based Input Data in Human Action Recognition
verfasst von
Jens Bayer
David Münch
Michael Arens
Copyright-Jahr
2021
Buch
Pattern Recognition. ICPR International Workshops and Challenges

Print ISBN: 978-3-030-68762-5

Electronic ISBN: 978-3-030-68763-2

Copyright-Jahr: 2021

DOI
https://doi.org/10.1007/978-3-030-68763-2_3