Online dictionary learning for sparse coding

By Julien Mairal, Francis R. Bach, Jean Ponce, Guillermo Sapiro. 2009

2,461 citations recorded by the source corpus.

Subfields: Computational Mechanics, Representation & Self-Supervised Learning, Optimization & Training, Signal Processing

How researchers see this paper

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

In Computational Mechanics

In Representation & Self-Supervised Learning

In Optimization & Training

In Signal Processing

Citations in the corpus

Feature Purification: How Adversarial Training Performs Robust Deep Learning (2020, background): “There are many existing theoretical works studying algorithm for sparse coding [9, 17, 43, 47, 54, 68, 85, 91, 94], however, these algorithms share little similarity to training a neural network.”
EDUCE: Explaining model Decisions through Unsupervised Concepts Extraction (2019, methodology): “Since h is a binary representation of x , our method is very close to sparse-coding techniques [17] where θ are its parameters.”
HOGgles: Visualizing Object Detection Features (2013, methodology): “ing problem with concatenated dictionaries, which we optimize using SPAMS [14].”
Deep Learning of Representations: Looking Forward (2013, background): “good news is that for sparse coding, MAP inference is a convex optimization problem for which several fast approximations have been proposed (Mairal et al., 2009; Gregor and LeCun, 2010a).”
Super-Resolution with Deep Convolutional Sufficient Statistics (2015, background): “Parametric models with sparse regularization have enjoyed great success in this problem (Elad & Aharon (2006); Yang et al. (2008)), thanks to their capacity to capture local regularity with efﬁcient convex optimization methods (Mairal et al. (2009)).”
Accelerated gradient methods for nonconvex nonlinear and stochastic programming (2013, background): “, [7,21]) consist of both convex and nonconvex components, corresponding to the data fidelity and sparsity regularization terms respectively.”
Sparsity-based image denoising via dictionary learning and structural clustering (2011, neutral): “, K-SVD [2], stochastic approximation [3]).”
Strathprints Institutional Repository Shuhui and Ren, Jinchang (2015) Effective and Efficient Midlevel Visual Elements-oriented Land-use Classification Using Vhr Remote Sensing Images. Ieee Transactions on Geoscience and Remote Sensing, 53 (8). Pp. 4238-4249. Issn 0196-2892 Effective and Efficient M (neutral): “…and activation vectors is obviously brittle, in which sparselets and activation vectors were approximately obtained by using greedy algorithms such as orthogonal matching pursuit algorithm (OMP) [25] [26] [27] without fully exploiting the discriminative information hidden in training samples.”
Machine learning in acoustics: Theory and applications. (2019, positive): “67 Dictionary learning has been applied in a number of acoustics problems.”
Discriminatively Activated Sparselets (2013, methodology): “In (Song et al., 2012), the task of learning the sparse-let model S from a training set of parameter blocks { b ki } was naturally posed as a sparse coding dictionary learning problem (Kreutz-Delgado et al., 2003; Mairal et al., 2009).”
Semi-coupled dictionary learning with applications to image super-resolution and photo-sketch synthesis (2012, methodology): “Learning a dictionary from example image patches has been attracting much interest, and some representative methods have been proposed, such as K-SVD [1], supervised dictionary learning [19], online dictionary learning [17], etc.”
Learning the Structural Vocabulary of a Network (2017, methodology): “4% reconstruction accuracy, also outperforming other methods, including PCA + SVD, ICA (Hyvarinen & Oja, 2000), nonnegative matrix factorization (Lin, 2007), and dictionary learning (Mairal et al., 2009).”
Robust Estimation of 3D Human Poses from a Single Image (2014, methodology): “Our approach pursues a set of sparse bases by enforcing an L1-norm regularization on the basis coefficients (as in [10]).”
Structured Sparse Principal Component Analysis (2009, methodology): “Update of U The update of U follows the technique suggested by [11].”