Weakly-supervised temporal localization via occurrence count learning

Schroeter, Julien, Sidorov, Kirill ORCID: https://orcid.org/0000-0001-7935-4132 and Marshall, David ORCID: https://orcid.org/0000-0003-2789-1395 2019. Weakly-supervised temporal localization via occurrence count learning. Presented at: 36th International Conference on Machine Learning, Long Beach, CA, USA, 9-15 June 2019. Published in: Chaudhuri, Kamalika and Salakhutdinov, Ruslan eds. Proceedings of Machine Learning Research. Volume 97: International Conference on Machine Learning, 9-15 June 2019, Long Beach, California, USA. Proceedings of Machine Learning Research. , vol.97 pp. 5649-5659.

Preview

PDF - Published Version Download (646kB) | Preview

Abstract

We propose a novel model for temporal detection and localization which allows the training of deep neural networks using only counts of event occurrences as training labels. This powerful weakly-supervised framework alleviates the burden of the imprecise and time consuming process of annotating event locations in temporal data. Unlike existing methods, in which localization is explicitly achieved by design, our model learns localization implicitly as a byproduct of learning to count instances. This unique feature is a direct consequence of the model’s theoretical properties. We validate the effectiveness of our approach in a number of experiments (drum hit and piano onset detection in audio, digit detection in images) and demonstrate performance comparable to that of fully-supervised state-of-the-art methods, despite much weaker training requirements.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Published Online
Status:	Published
Schools:	Advanced Research Computing @ Cardiff (ARCCA) Computer Science & Informatics
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software
ISSN:	2640-3498
Date of First Compliant Deposit:	14 August 2019
Date of Acceptance:	20 May 2019
Last Modified:	14 Jun 2024 15:36
URI:	https://orca.cardiff.ac.uk/id/eprint/124937

Citation Data

Cited 5 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item