Volltext-Downloads (blau) und Frontdoor-Views (grau)

An Extended Study of Human-like Behavior under Adversarial Training

  • Neural networks have a number of shortcomings. Amongst the severest ones is the sensitivity to distribution shifts which allows models to be easily fooled into wrong predictions by small perturbations to inputs that are often imperceivable to humans and do not have to carry semantic meaning. Adversarial training poses a partial solution to address this issue by training models on worst-caseNeural networks have a number of shortcomings. Amongst the severest ones is the sensitivity to distribution shifts which allows models to be easily fooled into wrong predictions by small perturbations to inputs that are often imperceivable to humans and do not have to carry semantic meaning. Adversarial training poses a partial solution to address this issue by training models on worst-case perturbations. Yet, recent work has also pointed out that the reasoning in neural networks is different from humans. Humans identify objects by shape, while neural nets mainly employ texture cues. Exemplarily, a model trained on photographs will likely fail to generalize to datasets containing sketches. Interestingly, it was also shown that adversarial training seems to favorably increase the shift toward shape bias. In this work, we revisit this observation and provide an extensive analysis of this effect on various architectures, the common L_2-and L_-training, and Transformer-based models. Further, we provide a possible explanation for this phenomenon from a frequency perspective.…zeige mehrzeige weniger

Metadaten exportieren

Weitere Dienste

Suche bei Google Scholar

Statistik

frontdoor_oas
Metadaten
Dokumentart:Konferenzveröffentlichung
Art der Konferenzveröffentlichung:Konferenzartikel
Zitierlink: https://opus.hs-offenburg.de/8240
Bibliografische Angaben
Titel (Englisch):An Extended Study of Human-like Behavior under Adversarial Training
Konferenzangaben:IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (17-24 June 2023 : Vancouver, BC, Canada)
Verfasserangaben:Paul GavrikovStaff MemberORCiDGND, Janis KeuperStaff MemberORCiDGND, Margret KeuperORCiD
Erscheinungsjahr:2023
Urhebende Körperschaft:Computer Vision Foundation
Erste Seite:2361
Letzte Seite:2368
Titel des übergeordneten Werkes (Englisch):Proceedings : 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops : CVPRW 2023
ISBN:979-8-3503-0249-3 (Elektronisch)
ISBN:979-8-3503-0250-9 (Print on Demand)
DOI:https://doi.org/10.1109/CVPRW59228.2023.00233
URL:https://openaccess.thecvf.com/content/CVPR2023W/AML/papers/Gavrikov_An_Extended_Study_of_Human-Like_Behavior_Under_Adversarial_Training_CVPRW_2023_paper.pdf
Sprache:Englisch
Inhaltliche Informationen
Fakultäten / Einrichtungen:Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019)
Forschung:IMLA - Institute for Machine Learning and Analytics
Sammlungen der Hochschule Offenburg:Bibliografie
Freies Schlagwort / Tag:Deep Leaning
Formale Angaben
Relevanz für "Jahresbericht über Forschungsleistungen":5-fach | Konferenzbeitrag
Open-Access-Status: Open Access 
 Grün 
Lizenz (Deutsch):License LogoUrheberrechtlich geschützt