Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
Zur Ablage hinzufügen
 Lokale TagsFreigabegeschichteDetailsÜbersicht
  Generalisation in humans and deep neural networks

Geirhos, R., Medina Temme, C., Rauber, J., Schuett, H., Bethge, M., & Wichmann, F. (2019). Generalisation in humans and deep neural networks. In S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, & R. Garnett (Eds.), Advances in Neural Information Processing Systems 31 (pp. 7549-7561). Red Hook, NY, USA: Curran.

Item is

 

einblenden: alle ausblenden: alle

Basisdaten

einblenden: ausblenden:
Datensatz-Permalink: https://hdl.handle.net/21.11116/0000-0002-0582-5 Versions-Permalink: https://hdl.handle.net/21.11116/0000-000A-11AC-1
Genre: Konferenzbeitrag

Externe Referenzen

einblenden:
ausblenden:
externe Referenz:
http://papers.nips.cc/paper/7982-generalisation-in-humans-and-deep-neural-networks.pdf (Verlagsversion)
Beschreibung:
-
OA-Status:

Urheber

einblenden:
ausblenden:
 Urheber:
Geirhos, R, Autor
Medina Temme, CR, Autor
Rauber, J, Autor
Schuett, HH, Autor
Bethge, M1, 2, Autor           
Wichmann, FA, Autor           
Affiliations:
1Research Group Computational Vision and Neuroscience, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497805              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: We compare the robustness of humans and current convolutional deep neural networks (DNNs) on object recognition under twelve different types of image degradations. First, using three well known DNNs (ResNet-152, VGG-19, GoogLeNet) we find the human visual system to be more robust to nearly all of the tested image manipulations, and we observe progressively diverging classification error-patterns between humans and DNNs when the signal gets weaker. Secondly, we show that DNNs trained directly on distorted images consistently surpass human performance on the exact distortion types they were trained on, yet they display extremely poor generalisation abilities when tested on other distortion types. For example, training on salt-and-pepper noise does not imply robustness on uniform white noise and vice versa. Thus, changes in the noise distribution between training and testing constitutes a crucial challenge to deep learning vision systems that can be systematically addressed in a lifelong machine learning approach. Our new dataset consisting of 83K carefully measured human psychophysical trials provide a useful reference for lifelong robustness against image degradations set by the human visual system.

Details

einblenden:
ausblenden:
Sprache(n):
 Datum: 2018-122019-07
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: -
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: Thirty-second Annual Conference on Neural Information Processing Systems 2018 (NeurIPS 2018)
Veranstaltungsort: Montréal, Canada
Start-/Enddatum: 2018-12-03 - 2018-12-08

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: Advances in Neural Information Processing Systems 31
Genre der Quelle: Konferenzband
 Urheber:
Bengio, S, Herausgeber
Wallach, HM, Herausgeber
Larochelle, H, Herausgeber
Grauman, K, Herausgeber
Cesa-Bianchi, N, Herausgeber
Garnett, R, Herausgeber
Affiliations:
-
Ort, Verlag, Ausgabe: Red Hook, NY, USA : Curran
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 7549 - 7561 Identifikator: ISBN: 978-1-5108-8447-2