Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Weakly-supervised temporal localization via occurrence count learning

Schroeter, Julien, Sidorov, Kirill and Marshall, Andrew David 2019. Weakly-supervised temporal localization via occurrence count learning. Presented at: International Conference on Machine Learning, Long Beach, California, USA, 9-15 June 2019. Proceedings of Machine Learning Research: Volume 97: International Conference on Machine Learning, 9-15 June 2019, Long Beach, California, USA. Long Beach, California, USA: PMLR, pp. 5649-5659.

[img]
Preview
PDF (ICML Conference Paper) - 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: Computer Science & Informatics
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Q Science > QA Mathematics > QA76 Computer software
Publisher: PMLR
Related URLs:
Date of First Compliant Deposit: 14 August 2019
Date of Acceptance: 20 May 2019
Last Modified: 15 Aug 2019 12:30
URI: http://orca-mwe.cf.ac.uk/id/eprint/124937

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics