Feature-wise transformations

Ethan Perez
Nathan Schucher
Florian Strub
Harm de Vries
Aaron Courville
Yoshua Bengio
Google Scholar


In this article, we dive into the subject of feature-wise transformations, showing that they find their way into a surprising number of recent neural network architectures used in various problem settings. We discuss feature-wise transformations as a family of related approaches and show how they can be conceptualized using the Feature-wise Linear Modulation (FiLM) nomenclature. We will then point out their numerous uses in the recent literature. Finally, we will take a look at interesting and intriguing properties that arise from the use of FiLM.

Research Areas