Structured sparse coding for image denoising or pattern detection

Karygianni, Sofia; Frossard, Pascal

doi:10.1109/icassp.2014.6854258

Cited by 6 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Structured sparsity has been widely used in practical problems, including model-based compressive sensing (Baraniuk et al, 2010;Asaei et al, 2011a;Duarte and Eldar, 2011;, signal processing (Bach and Jordan, 2006;Asaei et al, 2011;2014a;2014b;Najafian, 2016), computer vision (Jenatton et al, 2009;Kim et al, 2013;Karygianni and Frossard, 2014;Xiao et al, 2016), bioinformatics (Wille and Bühlmann, 2006;Zhang SZ et al, 2011;Kim and Xing, 2012), and recommendation systems (Koren et al, 2009;Takacs et al, 2009;Rendle and SchmidtThieme, 2010;Zhang ZK et al, 2011). This article focuses mainly on their formulations and algorithms.…”

Section: Aim and Scope Of This Papermentioning

confidence: 99%

A systematic review of structured sparse learning

Qiao

Zhang

et al. 2017

Frontiers Inf Technol Electronic Eng

View full text Add to dashboard Cite

High dimensional data arising from diverse scientific research fields and industrial development have led to increased interest in sparse learning due to model parsimony and computational advantage. With the assumption of sparsity, many computational problems can be handled efficiently in practice. Structured sparse learning encodes the structural information of the variables and has been quite successful in numerous research fields. With various types of structures discovered, sorts of structured regularizations have been proposed. These regularizations have greatly improved the efficacy of sparse learning algorithms through the use of specific structural information. In this article, we present a systematic review of structured sparse learning including ideas, formulations, algorithms, and applications. We present these algorithms in the unified framework of minimizing the sum of loss and penalty functions, summarize publicly accessible software implementations, and compare the computational complexity of typical optimization methods to solve structured sparse learning problems. In experiments, we present applications in unsupervised learning, for structured signal recovery and hierarchical image reconstruction, and in supervised learning in the context of a novel graph-guided logistic regression.

show abstract

Section: Aim and Scope Of This Papermentioning

confidence: 99%

A systematic review of structured sparse learning

Qiao

Zhang

et al. 2017

Frontiers Inf Technol Electronic Eng

View full text Add to dashboard Cite

show abstract

“…Different from robust pooling layers in [12], our declarative defender is designed to reconstruct each point cloud in a (learnable) structural space as a means of denoising. To this end, we borrow the idea from structured sparse coding [49,20,57] by representing each point as a linear combination of atoms in a dictionary. Together with the backbone networks, the training of our robust classifiers can lead to a bilevel optimization problem.…”

Section: Introductionmentioning

confidence: 99%

Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks with Implicit Gradients

Li¹,

Zhang²,

Zhong³

et al. 2022

Preprint

View full text Add to dashboard Cite

Deep neural networks for 3D point cloud classification, such as PointNet, have been demonstrated to be vulnerable to adversarial attacks. Current adversarial defenders often learn to denoise the (attacked) point clouds by reconstruction, and then feed them to the classifiers as input. In contrast to the literature, we propose a family of robust structured declarative classifiers for point cloud classification, where the internal constrained optimization mechanism can effectively defend adversarial attacks through implicit gradients. Such classifiers can be formulated using a bilevel optimization framework. We further propose an effective and efficient instantiation of our approach, namely, Lattice Point Classifier (LPC), based on structured sparse coding in the permutohedral lattice and 2D convolutional neural networks (CNNs) that is end-to-end trainable. We demonstrate state-of-the-art robust point cloud classification performance on ModelNet40 and ScanNet under seven different attackers. For instance, we achieve 89.51% and 83.16% test accuracy on each dataset under the recent JGBA attacker that outperforms DUP-Net and IF-Defense with PointNet by ∼70%. The demo code is available at https://zhang-vislab.github.io.

show abstract

“…Our model builds on our previous work on structured sparsity [11] and represents signals as sparse set of molecules, which are linear combinations of atoms from a redundant dictionary of elementary functions. It permits to efficiently represent the signal structures as parts or patterns; it builds richer priors than classical structured sparsity models that merely focus on the support of the signal representation and not the actual energy distribution.…”

Section: Introductionmentioning

confidence: 99%

Sparse molecular image representation

Karygianni

Frossard

2016

Journal of Visual Communication and Image Representation

Self Cite

View full text Add to dashboard Cite

Sparsity-based models have proven to be very effective in most image processing applications. The notion of sparsity has recently been extended to structured sparsity models where not only the number of components but also their support is important. This paper goes one step further and proposes a new model where signals are composed of a small number of molecules, which are each linear combinations of a few elementary functions in a dictionary. Our model takes into account the energy on the signal components in addition to their support. We study our prior in detail and propose a novel algorithm for sparse coding that permits the appearance of signal dependent versions of the molecules. Our experiments prove the benefits of the new image model in various restoration tasks and confirm the effectiveness of priors that extend sparsity in flexible ways especially in case of inverse problems with low quality data.

show abstract

Structured sparse coding for image denoising or pattern detection

Cited by 6 publications

References 14 publications

A systematic review of structured sparse learning

A systematic review of structured sparse learning

Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks with Implicit Gradients

Sparse molecular image representation

Contact Info

Product

Resources

About