Multi-Layer Convolutional Sparse Modeling: Pursuit and Dictionary Learning

by   Jeremias Sulam, et al.

The recently proposed Multi-Layer Convolutional Sparse Coding (ML-CSC) model, consisting of a cascade of convolutional sparse layers, provides a new interpretation of Convolutional Neural Networks (CNNs). Under this framework, the computation of the forward pass in a CNN is equivalent to a pursuit algorithm aiming to estimate the nested sparse representation vectors -- or feature maps -- from a given input signal. Despite having served as a pivotal connection between CNNs and sparse modeling, a deeper understanding of the ML-CSC is still lacking: there are no pursuit algorithms that can serve this model exactly, nor are there conditions to guarantee a non-empty model. While one can easily obtain signals that approximately satisfy the ML-CSC constraints, it remains unclear how to simply sample from the model and, more importantly, how one can train the convolutional filters from real data. In this work, we propose a sound pursuit algorithm for the ML-CSC model by adopting a projection approach. We provide new and improved bounds on the stability of the solution of such pursuit and we analyze different practical alternatives to implement this in practice. We show that the training of the filters is essential to allow for non-trivial signals in the model, and we derive an online algorithm to learn the dictionaries from real data, effectively resulting in cascaded sparse convolutional layers. Last, but not least, we demonstrate the applicability of the ML-CSC model for several applications in an unsupervised setting, providing competitive results. Our work represents a bridge between matrix factorization, sparse dictionary learning and sparse auto-encoders, and we analyze these connections in detail.


page 5

page 17

page 18

page 19


On Multi-Layer Basis Pursuit, Efficient Algorithms and Convolutional Neural Networks

Parsimonious representations in data modeling are ubiquitous and central...

Classification Stability for Sparse-Modeled Signals

Despite their impressive performance, deep convolutional neural networks...

WSEBP: A Novel Width-depth Synchronous Extension-based Basis Pursuit Algorithm for Multi-Layer Convolutional Sparse Coding

The pursuit algorithms integrated in multi-layer convolutional sparse co...

Convolutional Neural Networks Analyzed via Convolutional Sparse Coding

Convolutional neural networks (CNN) have led to many state-of-the-art re...

Multi Layer Sparse Coding: the Holistic Way

The recently proposed multi-layer sparse model has raised insightful con...

Towards Understanding Residual and Dilated Dense Neural Networks via Convolutional Sparse Coding

Convolutional neural network (CNN) and its variants have led to many sta...

Sparse Factorization Layers for Neural Networks with Limited Supervision

Whereas CNNs have demonstrated immense progress in many vision problems,...

Please sign up or login with your details

Forgot password? Click here to reset