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:
CNN-PS: CNN-Based Photometric Stereo for General Non-convex Surfaces Kapitel lesen Erstes Kapitel lesen

2018 | OriginalPaper | Buchkapitel

Improving Spatiotemporal Self-supervision by Deep Reinforcement Learning

verfasst von : Uta Büchler, Biagio Brattoli, Björn Ommer

Erschienen in: Computer Vision – ECCV 2018

Verlag: Springer International Publishing

Einloggen

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

search-config
loading …

Abstract

Self-supervised learning of convolutional neural networks can harness large amounts of cheap unlabeled data to train powerful feature representations. As surrogate task, we jointly address ordering of visual data in the spatial and temporal domain. The permutations of training samples, which are at the core of self-supervision by ordering, have so far been sampled randomly from a fixed preselected set. Based on deep reinforcement learning we propose a sampling policy that adapts to the state of the network, which is being trained. Therefore, new permutations are sampled according to their expected utility for updating the convolutional feature representation. Experimental evaluation on unsupervised and transfer learning tasks demonstrates competitive performance on standard benchmarks for image and video classification and nearest neighbor retrieval.

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 Broadcasting Convolutional Network for Visual Relational Reasoning
Nächstes Kapitel Learning to Look around Objects for Top-View Representations of Outdoor Scenes
Anhänge
Nur mit Berechtigung zugänglich
Fußnoten
2
This work has been supported in part by DFG grant OM81/1-1, the Heidelberg Academy of Science, and an Nvidia hardware donation.
 
Literatur
1.
Andrychowicz, M., et al.: Learning to learn by gradient descent by gradient descent. In: Advances in Neural Information Processing Systems, pp. 3981–3989 (2016)
2.
Bautista, M.A., Sanakoyeu, A., Ommer, B.: Deep unsupervised similarity learning using partially ordered sets. In: Proceedings of IEEE Computer Vision and Pattern Recognition (2017)
3.
Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: Proceedings of the 26th Annual International Conference on Machine Learning, pp. 41–48. ACM (2009)
4.
5.
Brattoli, B., Büchler, U., Wahl, A.S., Schwab, M.E., Ommer, B.: Lstm self-supervision for detailed behavior analysis. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
6.
Chang, H.S., Learned-Miller, E., McCallum, A.: Active bias: training more accurate neural networks by emphasizing high variance samples. In: Advances in Neural Information Processing Systems, pp. 1003–1013 (2017)
7.
Chen, Y., et al.: Learning to learn without gradient descent by gradient descent. In: International Conference on Machine Learning, pp. 748–756 (2017)
8.
Cruz, R.S., Fernando, B., Cherian, A., Gould, S.: Deeppermnet: visual permutation learning. In: CVPR (2017)
9.
Doersch, C., Gupta, A., Efros, A.A.: Unsupervised visual representation learning by context prediction. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1422–1430 (2015)
10.
11.
12.
13.
14.
15.
Fan, Y., Tian, F., Qin, T., Liu, T.Y.: Neural data filter for bootstrapping stochastic gradient descent (2016)
16.
Fernando, B., Bilen, H., Gavves, E., Gould, S.: Self-supervised video representation learning with odd-one-out networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017). http://​arxiv.​org/​abs/​1611.​06646
17.
18.
Graves, A., Bellemare, M.G., Menick, J., Munos, R., Kavukcuoglu, K.: Automated curriculum learning for neural networks (2017). arXiv preprint arXiv:​1704.​03003
19.
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRef
20.
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift (2015). arXiv preprint arXiv:​1502.​03167
21.
Jia, Y., et al.: Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM International Conference on Multimedia, pp. 675–678. ACM (2014)
22.
Krähenbühl, P., Doersch, C., Donahue, J., Darrell, T.: Data-dependent initializations of convolutional neural networks (2015). arXiv preprint arXiv:​1511.​06856
23.
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
24.
Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: a large video database for human motion recognition. In: Proceedings of the International Conference on Computer Vision (ICCV) (2011)
25.
Kumar, M.P., Packer, B., Koller, D.: Self-paced learning for latent variable models. In: Advances in Neural Information Processing Systems, pp. 1189–1197 (2010)
26.
Larsson, G., Maire, M., Shakhnarovich, G.: Colorization as a proxy task for visual understanding (2017). arXiv preprint arXiv:​1703.​04044
27.
Lee, H.Y., Huang, J.B., Singh, M.K., Yang, M.H.: Unsupervised representation learning by sorting sequences. In: IEEE International Conference on Computer Vision (ICCV) (2017)
28.
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)
29.
Luo, Z., Peng, B., Huang, D.A., Alahi, A., Fei-Fei, L.: Unsupervised learning of long-term motion dynamics for videos. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
30.
Milbich, T., Bautista, M., Sutter, E., Ommer, B.: Unsupervised video understanding by reconciliation of posture similarities. In: Proceedings of the IEEE International Conference on Computer Vision (2017)
31.
Misra, I., Zitnick, C.L., Hebert, M.: Unsupervised learning using sequential verification for action recognition (2016)
32.
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A.A., Veness, J., Bellemare, M.G., Graves, A., Riedmiller, M., Fidjeland, A.K., Ostrovski, G., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529 (2015)CrossRef
33.
Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by solving jigsaw puzzles. In: IEEE European Conference on Computer Vision (ECCV) (2016)
34.
35.
Noroozi, M., Vinjimoor, A., Favaro, P., Pirsiavash, H.: Boosting self-supervised learning via knowledge transfer. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018
36.
37.
38.
Patel, Y., Gomez, L., Rusiñol, M., Jawahar, C., Karatzas, D.: Self-supervised learning of visual features through embedding images into text topic spaces. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
39.
Pathak, D., Girshick, R., Dollár, P., Darrell, T., Hariharan, B.: Learning features by watching objects move. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
40.
Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2536–2544 (2016)
41.
Ravi, S., Larochelle, H.: Optimization as a model for few-shot learning (2016)
42.
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: Towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99 (2015)
43.
44.
Sanakoyeu, A., Bautista, M.A., Ommer, B.: Deep unsupervised learning of visual similarities. Pattern Recognit. 78, 331–343 (2018)CrossRef
45.
Silver, D., Huang, A., Maddison, C.J., Guez, A., Sifre, L., Van Den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484–489 (2016)CrossRef
46.
Soomro, K., Zamir, A.R., Shah, M.: Ucf101: a dataset of 101 human actions classes from videos in the wild (2012). arXiv preprint arXiv:​1212.​0402
47.
Sümer, Ö., Dencker, T., Ommer, B.: Self-supervised learning of pose embeddings from spatiotemporal relations in videos. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 4308–4317. IEEE (2017)
48.
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, vol. 1. MIT press, Cambridge (1998)
49.
Vondrick, C., Pirsiavash, H., Torralba, A.: Generating videos with scene dynamics. In: Conference on Neural Information Processing Systems (NIPS) (2016)
50.
Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: IEEE European Conference on Computer Vision (ECCV) (2016)
51.
Wang, X., Gupta, A.: Unsupervised learning of visual representations using videos. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2794–2802 (2015)
52.
Wang, X., He, K., Gupta, A.: Transitive invariance for self-supervised visual representation learning. In: IEEE International Conference on Computer Vision (ICCV) (2017)
53.
Williams, R.J., Peng, J.: Function optimization using connectionist reinforcement learning algorithms. Connect. Sci. 3(3), 241–268 (1991)CrossRef
54.
55.
Zhang, R., Isola, P., Efros, A.A.: Split-brain autoencoders: unsupervised learning by cross-channel prediction (2016). arXiv preprint arXiv:​1611.​09842
56.
Metadaten
Titel
Improving Spatiotemporal Self-supervision by Deep Reinforcement Learning
verfasst von
Uta Büchler
Biagio Brattoli
Björn Ommer
Copyright-Jahr
2018
Buch
Computer Vision – ECCV 2018

Print ISBN: 978-3-030-01266-3

Electronic ISBN: 978-3-030-01267-0

Copyright-Jahr: 2018

DOI
https://doi.org/10.1007/978-3-030-01267-0_47