FiLM: Visual Reasoning with a General Conditioning Layer (original) (raw)

Authors

• Ethan Perez
• Florian Strub Univ. Lille, CNRS, Centrale Lille, Inria, UMR 9189 CRIStAL France
• Harm de Vries MILA, Universite de Montreal
• Vincent Dumoulin MILA, Universite de Montreal
• Aaron Courville MILA, Universite de Montreal, CIFAR Fellow

DOI:

https://doi.org/10.1609/aaai.v32i1.11671

Keywords:

Deep Learning, Language and Vision

Abstract

We introduce a general-purpose conditioning method for neural networks called FiLM: Feature-wise Linear Modulation. FiLM layers influence neural network computation via a simple, feature-wise affine transformation based on conditioning information. We show that FiLM layers are highly effective for visual reasoning - answering image-related questions which require a multi-step, high-level process - a task which has proven difficult for standard deep learning methods that do not explicitly model reasoning. Specifically, we show on visual reasoning tasks that FiLM layers 1) halve state-of-the-art error for the CLEVR benchmark, 2) modulate features in a coherent manner, 3) are robust to ablations and architectural modifications, and 4) generalize well to challenging, new data from few examples or even zero-shot.

How to Cite

Perez, E., Strub, F., de Vries, H., Dumoulin, V., & Courville, A. (2018). FiLM: Visual Reasoning with a General Conditioning Layer. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). https://doi.org/10.1609/aaai.v32i1.11671

Issue

Section

AAAI Technical Track: Machine Learning