Ethan Perez, Florian Strub, Harm de Vries, Vincent Dumoulin, Aaron Courville · Proceedings of the AAAI Conference on Artificial Intelligence 2018 · 2018
DOI: 10.1609/aaai.v32i1.11671
Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).
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.
Last synced
This work has 1878 recorded citations, but citing papers have not been linked locally yet.
No comments yet — start the discussion below.