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:
Visual Odometry Based Omni-directional Hyperlapse Kapitel lesen Erstes Kapitel lesen

2018 | OriginalPaper | Buchkapitel

Dataset Augmentation with Synthetic Images Improves Semantic Segmentation

verfasst von : Manik Goyal, Param Rajpura, Hristo Bojinov, Ravi Hegde

Erschienen in: Computer Vision, Pattern Recognition, Image Processing, and Graphics

Verlag: Springer Singapore

Einloggen

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

search-config
loading …

Abstract

Although Deep Convolutional Neural Networks trained with strong pixel-level annotations have significantly pushed the performance in semantic segmentation, annotation efforts required for the creation of training data remains a roadblock for further improvements. We show that augmentation of the weakly annotated training dataset with synthetic images minimizes both the annotation efforts and also the cost of capturing images with sufficient variety. Evaluation on the PASCAL 2012 validation dataset shows an increase in mean IOU from 52.80% to 55.47% by adding just 100 synthetic images per object class. Our approach is thus a promising solution to the problems of annotation and dataset collection.

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 Exploring Memory and Time Efficient Neural Networks for Image Captioning
Nächstes Kapitel Deep Neural Network for Foreground Object Segmentation: An Unsupervised Approach
Literatur
1.
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: International Conference on Neural Information Processing Systems, pp. 1097–1105. Curran Associates Inc. (2012)
2.
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 07–12 June 2015, pp. 1–9. IEEE, June 2015
3.
Shelhamer, E., Long, J., Darrell, T.: Fully convolutional networks for semantic segmentation. arXiv Preprint arXiv:​1605.​06211, May 2016
4.
Badrinarayanan, V., Handa, A., Cipolla, R.: SegNet: a deep convolutional encoder-decoder architecture for robust semantic pixel-wise labelling. arXiv Preprint arXiv:​1505.​07293, May 2015
5.
Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. arXiv Preprint arXiv:​1606.​00915, June 2016
6.
Vezhnevets, A., Ferrari, V., Buhmann, J.M.: Weakly supervised structured output learning for semantic segmentation. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 845–852. IEEE, June 2012
7.
Verbeek, J., Triggs, B.: Region classification with Markov field aspect models. In: 2007 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8. IEEE, June 2007
8.
Xu, J., Schwing, A.G., Urtasun, R.: Tell me what you see and i will show you where it is. In: CVPR (2014)
9.
Everingham, M., Eslami, S.M.A., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes challenge: a retrospective. Int. J. Comput. Vis. 111(1), 98–136 (2015)CrossRef
10.
Hariharan, B., Arbelaez, P., Bourdev, L., Maji, S., Malik, J.: Semantic contours from inverse detectors. In: 2011 International Conference on Computer Vision, pp. 991–998. IEEE, November 2011
11.
12.
Pathak, D., Krähenbühl, P., Darrell, T.: Constrained convolutional neural networks for weakly supervised segmentation. arXiv Preprint arXiv:​1506.​03648, June 2015
13.
Pathak, D., Shelhamer, E., Long, J., Darrell, T.: Fully convolutional multi-class multiple instance learning. arXiv Preprint arXiv:​1412.​7144, December 2014
14.
Rother, C., Kolmogorov, V., Blake, A., Rother, C., Kolmogorov, V., Blake, A.: GrabCut. In: ACM SIGGRAPH 2004 Papers on - SIGGRAPH 2004, vol. 23, p. 309. ACM Press, New York (2004)
15.
Papandreou, G., Chen, L.C., Murphy, K.P., Yuille, A.L.: Weakly-and semi-supervised learning of a deep convolutional network for semantic image segmentation. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1742–1750. IEEE, December 2015
16.
Li, W., Duan, L., Xu, D., Tsang, I.W.: Learning with augmented features for supervised and semi-supervised heterogeneous domain adaptation. IEEE Trans. Pattern Anal. Mach. Intell. 36(6), 1134–1148 (2014)CrossRef
17.
Hoffman, J., Rodner, E., Donahue, J., Darrell, T., Saenko, K.: Efficient learning of domain-invariant image representations. arXiv Preprint arXiv:​1301.​3224, January 2013
18.
Hoffman, J., Guadarrama, S., Tzeng, E., Hu, R., Donahue, J., Girshick, R., Darrell, T., Saenko, K.: LSDA: large scale detection through adaptation. In: Proceedings of the 27th International Conference on Neural Information Processing Systems, pp. 3536–3544. MIT Press (2014)
19.
Kulis, B., Saenko, K., Darrell, T.: What you saw is not what you get: domain adaptation using asymmetric kernel transforms. In: CVPR 2011, pp. 1785–1792. IEEE, June 2011
20.
Long, M., Cao, Y., Wang, J., Jordan, M.I.: Learning transferable features with deep adaptation networks. In: Proceedings of the 32nd International Conference on International Conference on Machine Learning, vol. 37, pp. 97–105. JMLR.org (2015)
21.
Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks? In: Proceedings of the 27th International Conference on Neural Information Processing Systems, pp. 3320–3328. MIT Press (2014)
22.
Li, Y., Wang, N., Shi, J., Liu, J., Hou, X.: Revisiting batch normalization for practical domain adaptation. In: International Conference on Learning Representations Workshop (2017)
23.
Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. arXiv Preprint arXiv:​1604.​06646, April 2016
24.
Tzeng, E., Hoffman, J., Zhang, N., Saenko, K., Darrell, T.: Deep domain confusion: maximizing for domain invariance. arXiv Preprint arXiv:​1412.​3474, December 2014
25.
Ros, G., Sellart, L., Materzynska, J., Vazquez, D., Lopez, A.: The SYNTHIA dataset: a large collection of synthetic images for semantic segmentation of urban scenes. In: CVPR (2016)
26.
Peng, X., Saenko, K.: Synthetic to real adaptation with generative correlation alignment networks. arXiv Preprint arXiv:​1701.​05524, January 2017
27.
Peng, X., Sun, B., Ali, K., Saenko, K.: Learning deep object detectors from 3D models. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1278–1286. IEEE, December 2015
28.
Peng, X., Saenko, K.: Combining texture and shape cues for object recognition with minimal supervision. arXiv Preprint arXiv:​1609.​04356, September 2016
29.
30.
Xiao, J., Hays, J., Ehinger, K.A., Oliva, A., Torralba, A.: SUN database: large-scale scene recognition from abbey to zoo. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 3485–3492. IEEE, June 2010
31.
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE, June 2009
32.
Metadaten
Titel
Dataset Augmentation with Synthetic Images Improves Semantic Segmentation
verfasst von
Manik Goyal
Param Rajpura
Hristo Bojinov
Ravi Hegde
Copyright-Jahr
2018
Verlag
Springer Singapore
Buch
Computer Vision, Pattern Recognition, Image Processing, and Graphics

Print ISBN: 978-981-13-0019-6

Electronic ISBN: 978-981-13-0020-2

Copyright-Jahr: 2018

DOI
https://doi.org/10.1007/978-981-13-0020-2_31