1. ZHAW digitalcollection
  2. School of Engineering
  3. Publikationen
  4. Publikationen School of Engineering
Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-26095
Full metadata record
DC FieldValueLanguage
dc.contributor.authorTuggener, Lukas-
dc.contributor.authorSchmidhuber, Jürgen-
dc.contributor.authorStadelmann, Thilo-
dc.date.accessioned2022-11-17T11:24:32Z-
dc.date.available2022-11-17T11:24:32Z-
dc.date.issued2022-
dc.identifier.issn2624-9898de_CH
dc.identifier.urihttps://digitalcollection.zhaw.ch/handle/11475/26095-
dc.description.abstractClassification performance based on ImageNet is the de-facto standard metric for CNN development. In this work we challenge the notion that CNN architecture design solely based on ImageNet leads to generally effective convolutional neural network (CNN) architectures that perform well on a diverse set of datasets and application domains. To this end, we investigate and ultimately improve ImageNet as a basis for deriving such architectures. We conduct an extensive empirical study for which we train 500 CNN architectures, sampled from the broad AnyNetX design space, on ImageNet as well as 8 additional well known image classification benchmark datasets from a diverse array of application domains. We observe that the performances of the architectures are highly dataset dependent. Some datasets even exhibit a negative error correlation with ImageNet across all architectures. We show how to significantly increase these correlations by utilizing ImageNet subsets restricted to fewer classes. These contributions can have a profound impact on the way we design future CNN architectures and help alleviate the tilt we see currently in our community with respect to over-reliance on one dataset.de_CH
dc.language.isoende_CH
dc.publisherFrontiers Research Foundationde_CH
dc.relation.ispartofFrontiers in Computer Sciencede_CH
dc.rightshttp://creativecommons.org/licenses/by/4.0/de_CH
dc.subjectDeep learingde_CH
dc.subjectCNN architecture designde_CH
dc.subjectImageNetde_CH
dc.subjectEmpirical studyde_CH
dc.subject.ddc006: Spezielle Computerverfahrende_CH
dc.titleIs it enough to optimize CNN architectures on ImageNet?de_CH
dc.typeBeitrag in wissenschaftlicher Zeitschriftde_CH
dcterms.typeTextde_CH
zhaw.departementSchool of Engineeringde_CH
zhaw.organisationalunitCentre for Artificial Intelligence (CAI)de_CH
dc.identifier.doi10.3389/fcomp.2022.1041703de_CH
dc.identifier.doi10.21256/zhaw-26095-
zhaw.funding.euNode_CH
zhaw.issue1041703de_CH
zhaw.originated.zhawYesde_CH
zhaw.publication.statuspublishedVersionde_CH
zhaw.volume4de_CH
zhaw.publication.reviewPeer review (Publikation)de_CH
zhaw.webfeedMachine Perception and Cognitionde_CH
zhaw.webfeedDatalabde_CH
zhaw.webfeedZHAW digitalde_CH
zhaw.funding.zhawRealScore – Scanning of Real-World Sheet Music for a Digital Music Standde_CH
zhaw.author.additionalNode_CH
zhaw.display.portraitYesde_CH
zhaw.monitoring.costperiod2022de_CH
Appears in collections:Publikationen School of Engineering

Files in This Item:
File Description SizeFormat 
2022_Tuggener-Schmidhuber-Stadelmann_Optimize-CNN-ImageNet_fcomp.pdf7.98 MBAdobe PDFThumbnail
View/Open
Show simple item record
Tuggener, L., Schmidhuber, J., & Stadelmann, T. (2022). Is it enough to optimize CNN architectures on ImageNet? Frontiers in Computer Science, 4(1041703). https://doi.org/10.3389/fcomp.2022.1041703
Tuggener, L., Schmidhuber, J. and Stadelmann, T. (2022) ‘Is it enough to optimize CNN architectures on ImageNet?’, Frontiers in Computer Science, 4(1041703). Available at: https://doi.org/10.3389/fcomp.2022.1041703.
L. Tuggener, J. Schmidhuber, and T. Stadelmann, “Is it enough to optimize CNN architectures on ImageNet?,” Frontiers in Computer Science, vol. 4, no. 1041703, 2022, doi: 10.3389/fcomp.2022.1041703.
TUGGENER, Lukas, Jürgen SCHMIDHUBER und Thilo STADELMANN, 2022. Is it enough to optimize CNN architectures on ImageNet? Frontiers in Computer Science. 2022. Bd. 4, Nr. 1041703. DOI 10.3389/fcomp.2022.1041703
Tuggener, Lukas, Jürgen Schmidhuber, and Thilo Stadelmann. 2022. “Is It Enough to Optimize CNN Architectures on ImageNet?” Frontiers in Computer Science 4 (1041703). https://doi.org/10.3389/fcomp.2022.1041703.
Tuggener, Lukas, et al. “Is It Enough to Optimize CNN Architectures on ImageNet?” Frontiers in Computer Science, vol. 4, no. 1041703, 2022, https://doi.org/10.3389/fcomp.2022.1041703.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.