Recurrent Models of Visual Attention

By Volodymyr Mnih, Nicolas Manfred Otto Heess, Alex Graves, Koray Kavukcuoglu. 2014

3,987 citations recorded by the source corpus.

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.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition, Model Architectures, Human-Computer Interaction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

  1. Sergey Levine
  2. Yoshua Bengio
  3. Pieter Abbeel
  4. Nicolas Manfred Otto Heess
  5. J. Urgen Schmidhuber
  6. Chelsea Finn
  7. Josh Tenenbaum
  8. Jianbing Shen

In Computer Vision and Pattern Recognition

  1. Luc Van Gool
  2. Dacheng Tao
  3. Ming-Hsuan Yang
  4. Trevor Darrell
  5. Xiaogang Wang
  6. Jitendra Malik
  7. Yi Yang
  8. Andrew Zisserman

In Model Architectures

  1. Quoc V. Le
  2. Yoshua Bengio
  3. Kyunghyun Cho
  4. Ruslan Salakhutdinov
  5. Richard Socher
  6. Mohit Bansal
  7. J. Urgen Schmidhuber
  8. Jianfeng Gao

In Human-Computer Interaction

  1. Xiaogang Wang
  2. Wanli Ouyang
  3. Jitendra Malik
  4. G. Wang
  5. J. Urgen Schmidhuber
  6. Alan L. Yuille
  7. Xiaoou Tang
  8. Deva Ramanan

Citations in the corpus