FiLM: Visual Reasoning with a General Conditioning Layer
This addresses the challenge of visual reasoning for AI systems, offering a novel approach to improve performance on tasks that have been difficult for standard deep learning methods.
The paper tackles the problem of visual reasoning, which involves answering image-related questions requiring multi-step processes, by introducing FiLM (Feature-wise Linear Modulation) layers as a general-purpose conditioning method for neural networks. The result is that FiLM layers halve state-of-the-art error on the CLEVR benchmark and demonstrate robustness and generalization capabilities.
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.