Learning to combine foveal glimpses with a third-order Boltzmann machine

By Hugo Larochelle, Geoffrey E. Hinton. 2010

510 citations recorded by the source corpus.

Subfields: Representation & Self-Supervised Learning

How researchers see this paper

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

In Representation & Self-Supervised Learning

Citations in the corpus

DRAW: A Recurrent Neural Network For Image Generation (2015, background): “…that visual structure can be better captured by a sequence of partial glimpses, or foveations, than by a single sweep through the entire image (Larochelle & Hinton, 2010; Denil et al., 2012; Tang et al., 2013; Ranzato, 2014; Zheng et al., 2014; Mnih et al., 2014; Ba et al., 2014; Ser-manet et…”
Squeeze-and-Excitation Networks (2017, background): “Attention can be viewed, broadly, as a tool to bias the allocation of available processing resources towards the most informative components of an input signal [17, 18, 22, 29, 32].”
Recurrent Models of Visual Attention (2014, background): “Some works in the computer vision literature and elsewhere e.g. [2, 4, 6, 14, 16, 17, 20] have embraced vision as a sequential decision task as we do here.”
One-Shot Generalization in Deep Generative Models (2016, methodology): “Attention has been most widely used for classification tasks, having been shown to improve both scalability and generalization (Larochelle & Hinton, 2010; Chikkerur et al., 2010; Xu et al., 2015; Jaderberg et al., 2015; Mnih et al., 2014; Ba et al., 2015).”
Image Captioning with Semantic Attention (2016, methodology): “In terms of models, [21, 33] approach it with Boltzmann machines while [28] does with recurrent neural networks.”
BAM: Bottleneck Attention Module (2018, background): “In fact, this design follows the similar aspect of a human visual system, which has ‘what’ (channel) and ‘where’ (spatial) pathways and both pathways contribute to process visual information [6, 31].”
Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer (2016, methodology): “Early work on attention based tracking Larochelle & Hinton (2010), Denil et al. (2012) was motivated by human attention mechanism theories Rensink (2000) and was done via Restricted Bolz-mann Machines.”
Methods for interpreting and understanding deep neural networks (2017, methodology): “Post-hoc interpretability should be contrasted to incorporating interpretability directly into the structure of the model, as done, for example, in [54,17,76,37, 73].”
Residual Attention Network for Image Classification (2017, methodology): “Similar to our work, [25, 29, 21, 18] use residual learning with attention mechanism to benefit from residual learning.”
Explaining nonlinear classification decisions with deep Taylor decomposition (2015, background): “Attention models based on neural networks, trained to classify an image from only a few glimpses of it [40], readily provide a spatial interpretation for the clas-”
CBAM: Convolutional Block Attention Module (2018, background): “Instead, humans exploit a sequence of partial glimpses and selectively focus on salient parts in order to capture visual structure better [26].”
Pose-conditioned Spatio-Temporal Attention for Human Action Recognition (2017, positive): “Larochelle and Hinton [20] pioneered the incorporation of attention into a learning architecture by coupling Restricted Boltzmann Machines with a foveal representation.”
Deep Networks with Internal Selective Attention through Feedback Connections (2014, background): “In the context of computer vision, RL has been shown to be able to learn saccades in visual scenes to learn selective attention [40, 41], learn feedback to lower levels [42, 43], and improve face recognition [44, 45].”
Understanding the Effective Receptive Field in Deep Convolutional Neural Networks (2016, background): “Some neural networks have explicitly constructed representations of this form [11].”
Learning Where to Attend with Deep Architectures for Image Tracking (2011, methodology): “See Larochelle & Hinton (2010) for more details.”