Bitte benutzen Sie diese Kennung, um auf die Ressource zu verweisen:
https://doi.org/10.21256/zhaw-3850| Publikationstyp: | Konferenz: Paper |
| Art der Begutachtung: | Peer review (Publikation) |
| Titel: | Learning neural models for end-to-end clustering |
| Autor/-in: | Meier, Benjamin Bruno Elezi, Ismail Amirian, Mohammadreza Dürr, Oliver Stadelmann, Thilo |
| DOI: | 10.1007/978-3-319-99978-4_10 10.21256/zhaw-3850 |
| Tagungsband: | Artificial Neural Networks in Pattern Recognition |
| Seite(n): | 126 |
| Seiten bis: | 138 |
| Angaben zur Konferenz: | 8th IAPR TC3 Workshop on Artificial Neural Networks in Pattern Recognition (ANNPR), Siena, Italy, 19-21 September 2018 |
| Erscheinungsdatum: | 2018 |
| Reihe: | Lecture Notes in Computer Science |
| Reihenzählung: | 11081 |
| Verlag / Hrsg. Institution: | Springer |
| ISBN: | 978-3-319-99977-7 978-3-319-99978-4 |
| Sprache: | Englisch |
| Schlagwörter: | Perceptual grouping; Learning to cluster; Speech & image clustering |
| Fachgebiet (DDC): | 006: Spezielle Computerverfahren |
| Zusammenfassung: | We propose a novel end-to-end neural network architecture that, once trained, directly outputs a probabilistic clustering of a batch of input examples in one pass. It estimates a distribution over the number of clusters k, and for each 1 <= k <= k_max, a distribution over the individual cluster assignment for each data point. The network is trained in advance in a supervised fashion on separate data to learn grouping by any perceptual similarity criterion based on pairwise labels (same/different group). It can then be applied to different data containing different groups. We demonstrate promising performance on high-dimensional data like images (COIL-100) and speech (TIMIT). We call this “learning to cluster” and show its conceptual difference to deep metric learning, semi-supervise clustering and other related approaches while having the advantage of performing learnable clustering fully end-to-end. |
| URI: | https://digitalcollection.zhaw.ch/handle/11475/7727 |
| Volltext Version: | Akzeptierte Version |
| Lizenz (gemäss Verlagsvertrag): | Keine Angabe |
| Departement: | School of Engineering |
| Organisationseinheit: | Institut für Informatik (InIT) Institut für Datenanalyse und Prozessdesign (IDP) |
| Enthalten in den Sammlungen: | Publikationen School of Engineering |
Dateien zu dieser Ressource:
| Datei | Beschreibung | Größe | Format | |
|---|---|---|---|---|
| ANNPR_2018a.pdf | Accepted Version | 3.51 MB | Adobe PDF |  Öffnen/Anzeigen |
Zur Langanzeige
Meier, B. B., Elezi, I., Amirian, M., Dürr, O., & Stadelmann, T. (2018). Learning neural models for end-to-end clustering [Conference paper]. Artificial Neural Networks in Pattern Recognition, 126–138. https://doi.org/10.1007/978-3-319-99978-4_10
Meier, B.B. et al. (2018) ‘Learning neural models for end-to-end clustering’, in Artificial Neural Networks in Pattern Recognition. Springer, pp. 126–138. Available at: https://doi.org/10.1007/978-3-319-99978-4_10.
B. B. Meier, I. Elezi, M. Amirian, O. Dürr, and T. Stadelmann, “Learning neural models for end-to-end clustering,” in Artificial Neural Networks in Pattern Recognition, 2018, pp. 126–138. doi: 10.1007/978-3-319-99978-4_10.
MEIER, Benjamin Bruno, Ismail ELEZI, Mohammadreza AMIRIAN, Oliver DÜRR und Thilo STADELMANN, 2018. Learning neural models for end-to-end clustering. In: Artificial Neural Networks in Pattern Recognition. Conference paper. Springer. 2018. S. 126–138. ISBN 978-3-319-99977-7
Meier, Benjamin Bruno, Ismail Elezi, Mohammadreza Amirian, Oliver Dürr, and Thilo Stadelmann. 2018. “Learning Neural Models for End-to-End Clustering.” Conference paper. In Artificial Neural Networks in Pattern Recognition, 126–38. Springer. https://doi.org/10.1007/978-3-319-99978-4_10.
Meier, Benjamin Bruno, et al. “Learning Neural Models for End-to-End Clustering.” Artificial Neural Networks in Pattern Recognition, Springer, 2018, pp. 126–38, https://doi.org/10.1007/978-3-319-99978-4_10.
Alle Ressourcen in diesem Repository sind urheberrechtlich geschützt, soweit nicht anderweitig angezeigt.