Complex cell pooling and the statistics of natural images

By Aapo Hyvärinen, Urs Köster. 2007

78 citations recorded by the source corpus.

Subfields: Biophysics, Cognitive Neuroscience

How researchers see this paper

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

In Biophysics

In Cognitive Neuroscience

Citations in the corpus

Convolutional neural networks applied to house numbers digit classification (2012, background): “Lp pooling is a biologically inspired pooling layer modelled on complex cells [13, 5] who’s operation can be summarized in equation (1), where G is a Gaussian kernel, I is the input feature map and O is the output feature map.”
Learned-Norm Pooling for Deep Feedforward and Recurrent Neural Networks (2013, background): “In [18], the possibility of learning p has been investigated in a probabilistic setting in computer vision.”
Lp-Nested Symmetric Distributions (2010, methodology): “Equation (11) has an interesting special case when considering the joint distribution of the root node’s children.”
A Two-Layer Model of Natural Stimuli Estimated with Score Matching (2010, methodology): “Details of this preprocessing can be found in Hyvärinen and Köster (2007). The preprocessing can be given a physiological justification in terms of the processing in the retina and lateral geniculate nucleus, or it can be viewed more pragmatically as simplifying the statistical structure of the imag”
Learning invariant features through topographic filter maps (2009, methodology): “The idea relies on imposing sparsiﬁcation criteria on small groups of ﬁlter outputs [10, 6, 8], which can be related to the Group Lasso method for regularization [27].”
Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review (2017, background): “To address these issues, a viable alternative is the biologically inspired Lp pooling, which is modeled on complex cells (Simoncelli & Heeger, 1998; Hyvärinen & Köster, 2007).”