Gradient-based learning of higher-order image features

By Roland Memisevic. 2011

70 citations recorded by the source corpus.

Subfields: Biophysics, Computer Vision and Pattern Recognition, Media Technology

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 Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

A practical tutorial on autoencoders for nonlinear feature fusion: Taxonomy, models, software and guidelines (2018, background): “The relational or “cross-correlation” AE deﬁned in [92] incorporates layers where units are combined by multiplication instead of by a weighted sum.”
Modeling Deep Temporal Dependencies with Recurrent "Grammar Cells" (2014, methodology): “This suggests modeling x (2) using a feature learning model whose parameters are a function of x (1) [14], giving rise to bi-linear models of transformations , such as the Gated Boltzmann Machine [15] [3], Gated Autoencoder [16], and similar models (see [14] for an overview).”
Solid Harmonic Wavelet Scattering for Predictions of Molecule Properties (2018, background): “For r = 2 this form introduces a non-linearity similar to those found in factored gated autoencoders 34 .”
Towards Deep Developmental Learning (2016, background): “whereas gated auto-encoders (GAEs), illustrated in 2, were proposed in [70].”
Unsupervised Learning of Visual Representations using Videos (2015, methodology): “Memisevic (2011) proposed Gated Autoencoders which are same as GRBMs, except that the generative probabilistic model is replaced by an autoencoder with sparsity.”
A Review on Deep Learning Techniques for Video Prediction (2020, background): “where f is a bilinear interpolator such as [7], [156], [157], (u, v) is a motion vector predicted by G, and Xt(x, y) is a pixel value at (x,y) in the last observed frame Xt.”
On autoencoder scoring (2013, background): “…to yield state-of-the-art performance in a wide variety of tasks, ranging from object recognition and learning invariant representations to syntatic modeling of text (Le et al., 2012; Socher et al., 2011; Rolfe & LeCun, 2013; Swersky et al., 2011; Vincent, 2011; Memisevic, 2011; Zou et al., 2012).”
Solid Harmonic Wavelet Scattering: Predicting Quantum Molecular Energy from Invariant Descriptors of 3D Electronic Densities (2017, background): “For r = 2 this form introduces a non-linearity similar to those found in factored gated autoencoders [14].”
Unsupervised learning of depth and motion (2013, methodology): “Here, we assume an autoencoder with tied weights similar to [17, 11, 9].”