Supervised Dictionary Learning

Abstract

It is now well established that sparse signal models are well suited to restoration tasks and can effectively be learned from audio, image, and video data. Recent research has been aimed at learning discriminative sparse models instead of purely reconstructive ones. This paper proposes a new step in that direction, with a novel sparse representation for signals belonging to different classes in terms of a shared dictionary and multiple class-decision functions. The linear variant of the proposed model admits a simple probabilistic interpretation, while its most general variant admits an interpretation in terms of kernels. An optimization framework for learning all the components of the proposed model is presented, along with experimental results on standard handwritten digit and texture classification tasks.

References in corpus (11)

• Least Angle Regression
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Rejoinder to "Least angle regression" by Efron et al
• Supervised Topic Models

Cited by in corpus (95)

• A survey of sparse representation: algorithms and applications
• Task-Driven Dictionary Learning
• Proximal Methods for Hierarchical Sparse Coding
• Dictionary Learning over Distributed Models
• Augmenting Supervised Neural Networks with Unsupervised Objectives for Large-scale Image Classification
• Information Constraints on Auto-Encoding Variational Bayes
• Linearized Kernel Dictionary Learning
• Kernelized Supervised Dictionary Learning
• Structured sparsity-inducing norms through submodular functions
• Network Representation Learning: A Survey
• A Unified Semantic Embedding: Relating Taxonomies and Attributes
• Stochastic Coordinate Coding and Its Application for Drosophila Gene Expression Pattern Annotation
• Sparse Activity and Sparse Connectivity in Supervised Learning
• The Sample Complexity of Dictionary Learning
• Supervised Dictionary Learning and Sparse Representation-A Review
• "Convex Until Proven Guilty": Dimension-Free Acceleration of Gradient Descent on Non-Convex Functions
• Discriminative Recurrent Sparse Auto-Encoders
• Score Function Features for Discriminative Learning: Matrix and Tensor Framework
• Algorithms for stochastic optimization with functional or expectation constraints
• Divide and Conquer: An Incremental Sparsity Promoting Compressive Sampling Approach for Polynomial Chaos Expansions
• Structure-Aware Classification using Supervised Dictionary Learning
• Auxiliary Image Regularization for Deep CNNs with Noisy Labels
• Robust Non-Linear Matrix Factorization for Dictionary Learning, Denoising, and Clustering
• Greedy Deep Dictionary Learning
• A Brief Summary of Dictionary Learning Based Approach for Classification
• Cross-domain Joint Dictionary Learning for ECG Inference from PPG
• A Deep Generative Deconvolutional Image Model
• Class-Incremental Few-Shot Object Detection
• TGAN: Deep Tensor Generative Adversarial Nets for Large Image Generation
• Weakly-supervised Dictionary Learning
• Discriminative Features via Generalized Eigenvectors
• Exploitation of Image Statistics with Sparse Coding in the Case of Stereo Vision
• Nonnegative Matrix Factorization for Semi-supervised Dimensionality Reduction
• Online Learning for Matrix Factorization and Sparse Coding
• Deep Transform and Metric Learning Network: Wedding Deep Dictionary Learning and Neural Networks
• Complete Dictionary Learning via ${\ell }^4$-Norm Maximization over the Orthogonal Group
• The Utility of Sparse Representations for Control in Reinforcement Learning
• Dictionary Learning with Equiprobable Matching Pursuit
• An improved analysis of the ER-SpUD dictionary learning algorithm
• Computational Intractability of Dictionary Learning for Sparse Representation
• Jitter-Adaptive Dictionary Learning - Application to Multi-Trial Neuroelectric Signals
• On the Sample Complexity of Predictive Sparse Coding
• Deep Network Classification by Scattering and Homotopy Dictionary Learning
• A novel multivariate performance optimization method based on sparse coding and hyper-predictor learning
• Sparse distributed localized gradient fused features of objects
• Ensemble Sparse Models for Image Analysis
• Recovery from Linear Measurements with Complexity-Matching Universal Signal Estimation
• Jointly Learning Non-negative Projection and Dictionary with Discriminative Graph Constraints for Classification
• A Forward Backward Greedy approach for Sparse Multiscale Learning
• Reconstruction of Ordinary Differential Equations From Time Series Data
• Statistical Physics and Information Theory Perspectives on Linear Inverse Problems
• A Benchmark for Sparse Coding: When Group Sparsity Meets Rank Minimization
• Supervised Dimensionality Reduction for Big Data
• Learning Combinations of Sigmoids Through Gradient Estimation
• Decentralized Dictionary Learning Over Time-Varying Digraphs
• Evolutionary Simplicial Learning as a Generative and Compact Sparse Framework for Classification
• Dictionary Learning for Channel Estimation in Hybrid Frequency-Selective mmWave MIMO Systems
• Sparse Dictionary-based Attributes for Action Recognition and Summarization
• A Study on Unsupervised Dictionary Learning and Feature Encoding for Action Classification
• Online Convex Matrix Factorization with Representative Regions
• Functional Regularization for Representation Learning: A Unified Theoretical Perspective
• Earthquake Detection in 1-D Time Series Data with Feature Selection and Dictionary Learning
• Non-Gaussian Discriminative Factor Models via the Max-Margin Rank-Likelihood
• Sentiment Analysis by Joint Learning of Word Embeddings and Classifier
• Collaborative Filtering and Multi-Label Classification with Matrix Factorization
• A Probabilistic Framework for Discriminative Dictionary Learning
• Fast Rotational Sparse Coding
• On the Invariance of Dictionary Learning and Sparse Representation to Projecting Data to a Discriminative Space
• Data-driven audio recognition: a supervised dictionary approach
• Semi-supervised Dictionary Learning Based on Hilbert-Schmidt Independence Criterion
• Supervised Quantization for Similarity Search
• Exemplar Based Deep Discriminative and Shareable Feature Learning for Scene Image Classification
• Analysis Dictionary Learning: An Efficient and Discriminative Solution
• Information-theoretic Dictionary Learning for Image Classification
• RandNet: deep learning with compressed measurements of images
• LinksIQ: Robust and Efficient Modulation Recognition with Imperfect Spectrum Scans
• Multilinear Map Layer: Prediction Regularization by Structural Constraint
• When coding meets ranking: A joint framework based on local learning
• Online Optimization for Large-Scale Max-Norm Regularization
• Multivariate Convolutional Sparse Coding with Low Rank Tensor
• Eigen component analysis: A quantum theory incorporated machine learning technique to find linearly maximum separable components
• Deep Iteration Assisted by Multi-level Obey-pixel Network Discriminator (DIAMOND) for Medical Image Recovery
• What is the Best Feature Learning Procedure in Hierarchical Recognition Architectures?
• Semi-supervised Sparse Representation with Graph Regularization for Image Classification
• EDIZ: An Error Diffusion Image Zooming Scheme
• Learning from Incomplete Features by Simultaneous Training of Neural Networks and Sparse Coding
• Fast Convolutional Sparse Coding in the Dual Domain
• Dictionary learning under global sparsity constraint
• Classification of Chinese Handwritten Numbers with Labeled Projective Dictionary Pair Learning
• Deep Learning Meets Projective Clustering
• Joint Learning of Discriminative Low-dimensional Image Representations Based on Dictionary Learning and Two-layer Orthogonal Projections
• Semantic Diversity versus Visual Diversity in Visual Dictionaries
• ProLFA: Representative Prototype Selection for Local Feature Aggregation
• Sparse Coding on Cascaded Residuals
• Targeted Source Detection for Environmental Data