Online Learning on Non-Stationary Data Streams for Image Recognition using Deep Embeddings

Vaquet V, Hinder F, Vaquet J, Brinkrolf J, Hammer B (2021)
IEEE Symposium Series on Computational Intelligence: 1-7.

Konferenzbeitrag | Veröffentlicht | Englisch
 
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
herausgebende Körperschaft
IEEE
Abstract / Bemerkung
Deep neural networks offer state-of-the-art technologies for highly nonlinear domains such as image processing; yet their initial training requires large amounts of data, such that they are not directly suited for online learning scenarios for streaming data where class distributions or class labels may change over time. In this contribution, we investigate the suitability of a combination of recent online learning technologies, which have been proposed for learning with streaming data and concept drift in simpler settings, and deep representations of image data as provided by deep networks trained in batch mode, to offer flexible learning technologies for streaming data from the image domain.
Erscheinungsjahr
2021
forms.conference.field.series_title_volume.series_title.label
IEEE Symposium Series on Computational Intelligence
Seite(n)
1-7
Konferenz
2021 IEEE Symposium Series on Computational Intelligence (SSCI)
Konferenzort
Orlando, FL, USA
Konferenzdatum
2021-12-5 – 2021-12-7
Page URI
https://pub.uni-bielefeld.de/record/2960687

Zitieren

Vaquet V, Hinder F, Vaquet J, Brinkrolf J, Hammer B. Online Learning on Non-Stationary Data Streams for Image Recognition using Deep Embeddings. IEEE Symposium Series on Computational Intelligence. 2021:1-7.
Vaquet, V., Hinder, F., Vaquet, J., Brinkrolf, J., & Hammer, B. (2021). Online Learning on Non-Stationary Data Streams for Image Recognition using Deep Embeddings. IEEE Symposium Series on Computational Intelligence, 1-7. https://doi.org/10.1109/SSCI50451.2021.9659903
Vaquet, V., Hinder, F., Vaquet, J., Brinkrolf, J., and Hammer, B. (2021). Online Learning on Non-Stationary Data Streams for Image Recognition using Deep Embeddings. IEEE Symposium Series on Computational Intelligence, 1-7.
Vaquet, V., et al., 2021. Online Learning on Non-Stationary Data Streams for Image Recognition using Deep Embeddings. IEEE Symposium Series on Computational Intelligence, , p 1-7.
V. Vaquet, et al., “Online Learning on Non-Stationary Data Streams for Image Recognition using Deep Embeddings”, IEEE Symposium Series on Computational Intelligence, 2021, pp. 1-7.
Vaquet, V., Hinder, F., Vaquet, J., Brinkrolf, J., Hammer, B.: Online Learning on Non-Stationary Data Streams for Image Recognition using Deep Embeddings. IEEE Symposium Series on Computational Intelligence. 1-7 (2021).
Vaquet, Valerie, Hinder, Fabian, Vaquet, Jonas, Brinkrolf, Johannes, and Hammer, Barbara. “Online Learning on Non-Stationary Data Streams for Image Recognition using Deep Embeddings”. IEEE Symposium Series on Computational Intelligence (2021): 1-7.

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar