FiLM: Visual Reasoning with a General Conditioning Layer
Ethan Perez, Florian Strub, Harm de Vries, Vincent Dumoulin, Aaron Courville
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/ethanjperez/filmOfficialIn paperpytorch★ 0
- github.com/jjgo/hyperlightpytorch★ 41
- github.com/CPJKU/audio_conditioned_unetpytorch★ 25
- github.com/caffeinism/film-pytorchpytorch★ 0
- github.com/keonlee9420/Daft-Exprtpytorch★ 0
- github.com/kdaip/stablettspytorch★ 0
- github.com/GuessWhatGame/clevrtf★ 0
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.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| MIT-States | FiLM | Recall@1 | 10.1 | — | Unverified |