Skip to yearly menu bar Skip to main content


Weakly-Supervised Temporal Localization via Occurrence Count Learning

Julien Schroeter · Kirill Sidorov · David Marshall

Pacific Ballroom #255

Keywords: [ Unsupervised and Semi-supervised Learning ] [ Time Series and Sequence Models ] [ Other Applications ] [ Deep Sequence Models ]


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.

Live content is unavailable. Log in and register to view live content