%0 Journal Article
%T Recurrent Models of Visual Attention
%A Volodymyr Mnih
%A Nicolas Heess
%A Alex Graves
%A Koray Kavukcuoglu
%J Computer Science
%D 2014
%I arXiv
%X Applying convolutional neural networks to large images is computationally expensive because the amount of computation scales linearly with the number of image pixels. We present a novel recurrent neural network model that is capable of extracting information from an image or video by adaptively selecting a sequence of regions or locations and only processing the selected regions at high resolution. Like convolutional neural networks, the proposed model has a degree of translation invariance built-in, but the amount of computation it performs can be controlled independently of the input image size. While the model is non-differentiable, it can be trained using reinforcement learning methods to learn task-specific policies. We evaluate our model on several image classification tasks, where it significantly outperforms a convolutional neural network baseline on cluttered images, and on a dynamic visual control problem, where it learns to track a simple object without an explicit training signal for doing so.
%U http://arxiv.org/abs/1406.6247v1