papers AI Learner
The Github is limit! Click to go to the new site.

Weakly-Supervised Temporal Localization via Occurrence Count Learning

2019-05-17
Julien Schroeter, Kirill Sidorov, David Marshall

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.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.07293

PDF

http://arxiv.org/pdf/1905.07293


Similar Posts

Comments