FiLM: Visual Reasoning with a General ...
Type de document :
Communication dans un congrès avec actes
Titre :
FiLM: Visual Reasoning with a General Conditioning Layer
Auteur(s) :
Perez, Ethan [Auteur]
Rice University [Houston]
Strub, Florian [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Sequential Learning [SEQUEL]
de Vries, Harm [Auteur]
Dumoulin, Vincent [Auteur]
Courville, Aaron [Auteur]
Rice University [Houston]
Strub, Florian [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Sequential Learning [SEQUEL]
de Vries, Harm [Auteur]
Dumoulin, Vincent [Auteur]
Courville, Aaron [Auteur]
Titre de la manifestation scientifique :
AAAI Conference on Artificial Intelligence
Ville :
New Orleans
Pays :
Etats-Unis d'Amérique
Date de début de la manifestation scientifique :
2018-02-02
Discipline(s) HAL :
Informatique [cs]/Réseau de neurones [cs.NE]
Informatique [cs]/Intelligence artificielle [cs.AI]
Informatique [cs]/Intelligence artificielle [cs.AI]
Résumé en anglais : [en]
We introduce a general-purpose conditioning method for neu-ral networks called FiLM: Feature-wise Linear Modulation. FiLM layers influence neural network computation via a simple , feature-wise affine transformation based ...
Lire la suite >We introduce a general-purpose conditioning method for neu-ral 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.Lire moins >
Lire la suite >We introduce a general-purpose conditioning method for neu-ral 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.Lire moins >
Langue :
Anglais
Comité de lecture :
Oui
Audience :
Internationale
Vulgarisation :
Non
Collections :
Source :
Fichiers
- http://arxiv.org/pdf/1707.03017
- Accès libre
- Accéder au document
- 1707.03017
- Accès libre
- Accéder au document