Portrait de Florian Strub n'est pas disponible

Florian Strub

Alumni

Publications

Learning Visual Reasoning Without Strong Priors
Ethan Perez
Harm de Vries
Florian Strub
Vincent Dumoulin
Aaron Courville
Achieving artificial visual reasoning - the ability to answer image-related questions which require a multi-step, high-level process - is an… (voir plus) important step towards artificial general intelligence. This multi-modal task requires learning a question-dependent, structured reasoning process over images from language. Standard deep learning approaches tend to exploit biases in the data rather than learn this underlying structure, while leading methods learn to visually reason successfully but are hand-crafted for reasoning. We show that a general-purpose, Conditional Batch Normalization approach achieves state-of-the-art results on the CLEVR Visual Reasoning benchmark with a 2.4% error rate. We outperform the next best end-to-end method (4.5%) and even methods that use extra supervision (3.1%). We probe our model to shed light on how it reasons, showing it has learned a question-dependent, multi-step process. Previous work has operated under the assumption that visual reasoning calls for a specialized architecture, but we show that a general architecture with proper conditioning can learn to visually reason effectively.
2017-07-10
ArXiv (prépublication)
arxiv.org
arxiv.org
Modulating early visual processing by language
Harm de Vries
Florian Strub
Jérémie Mary
Hugo Larochelle
Olivier Pietquin
Aaron Courville
It is commonly assumed that language refers to high-level visual concepts while leaving low-level visual processing unaffected. This view do… (voir plus)minates the current literature in computational models for language-vision tasks, where visual and linguistic input are mostly processed independently before being fused into a single representation. In this paper, we deviate from this classic pipeline and propose to modulate the \emph{entire visual processing} by linguistic input. Specifically, we condition the batch normalization parameters of a pretrained residual network (ResNet) on a language embedding. This approach, which we call MOdulated RESnet (\MRN), significantly improves strong baselines on two visual question answering tasks. Our ablation study shows that modulating from the early stages of the visual processing is beneficial.
2017-07-02
ArXiv (prépublication)
arxiv.org
arxiv.org
Modulating early visual processing by language
Harm de Vries
Florian Strub
Jérémie Mary
Hugo Larochelle
Olivier Pietquin
Aaron Courville
It is commonly assumed that language refers to high-level visual concepts while leaving low-level visual processing unaffected. This view do… (voir plus)minates the current literature in computational models for language-vision tasks, where visual and linguistic input are mostly processed independently before being fused into a single representation. In this paper, we deviate from this classic pipeline and propose to modulate the \emph{entire visual processing} by linguistic input. Specifically, we condition the batch normalization parameters of a pretrained residual network (ResNet) on a language embedding. This approach, which we call MOdulated RESnet (\MRN), significantly improves strong baselines on two visual question answering tasks. Our ablation study shows that modulating from the early stages of the visual processing is beneficial.
arxiv.org