Bitte benutzen Sie diese Kennung, um auf die Ressource zu verweisen:
https://doi.org/10.21256/zhaw-26095
Publikationstyp: | Beitrag in wissenschaftlicher Zeitschrift |
Art der Begutachtung: | Peer review (Publikation) |
Titel: | Is it enough to optimize CNN architectures on ImageNet? |
Autor/-in: | Tuggener, Lukas Schmidhuber, Jürgen Stadelmann, Thilo |
et. al: | No |
DOI: | 10.3389/fcomp.2022.1041703 10.21256/zhaw-26095 |
Erschienen in: | Frontiers in Computer Science |
Band(Heft): | 4 |
Heft: | 1041703 |
Erscheinungsdatum: | 2022 |
Verlag / Hrsg. Institution: | Frontiers Research Foundation |
ISSN: | 2624-9898 |
Sprache: | Englisch |
Schlagwörter: | Deep learing; CNN architecture design; ImageNet; Empirical study |
Fachgebiet (DDC): | 006: Spezielle Computerverfahren |
Zusammenfassung: | Classification 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. |
URI: | https://digitalcollection.zhaw.ch/handle/11475/26095 |
Volltext Version: | Publizierte Version |
Lizenz (gemäss Verlagsvertrag): | CC BY 4.0: Namensnennung 4.0 International |
Departement: | School of Engineering |
Organisationseinheit: | Centre for Artificial Intelligence (CAI) |
Publiziert im Rahmen des ZHAW-Projekts: | RealScore – Scanning of Real-World Sheet Music for a Digital Music Stand |
Enthalten in den Sammlungen: | Publikationen School of Engineering |
Dateien zu dieser Ressource:
Datei | Beschreibung | Größe | Format | |
---|---|---|---|---|
2022_Tuggener-Schmidhuber-Stadelmann_Optimize-CNN-ImageNet_fcomp.pdf | 7.98 MB | Adobe PDF | Öffnen/Anzeigen |
Zur Langanzeige
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.
Alle Ressourcen in diesem Repository sind urheberrechtlich geschützt, soweit nicht anderweitig angezeigt.