DeepAI AI Chat
Log In Sign Up

An Efficient Approximate Method for Online Convolutional Dictionary Learning

01/25/2023
by   Farshad G. Veshki, et al.
aalto
0

Most existing convolutional dictionary learning (CDL) algorithms are based on batch learning, where the dictionary filters and the convolutional sparse representations are optimized in an alternating manner using a training dataset. When large training datasets are used, batch CDL algorithms become prohibitively memory-intensive. An online-learning technique is used to reduce the memory requirements of CDL by optimizing the dictionary incrementally after finding the sparse representations of each training sample. Nevertheless, learning large dictionaries using the existing online CDL (OCDL) algorithms remains highly computationally expensive. In this paper, we present a novel approximate OCDL method that incorporates sparse decomposition of the training samples. The resulting optimization problems are addressed using the alternating direction method of multipliers. Extensive experimental evaluations using several image datasets show that the proposed method substantially reduces computational costs while preserving the effectiveness of the state-of-the-art OCDL algorithms.

READ FULL TEXT

page 6

page 7

page 8

page 9

page 10

04/27/2018

Online Convolutional Sparse Coding with Sample-Dependent Dictionary

Convolutional sparse coding (CSC) has been popularly used for the learni...
08/31/2017

Online Convolutional Dictionary Learning

Convolutional sparse representations are a form of sparse representation...
06/21/2017

Scalable Online Convolutional Sparse Coding

Convolutional sparse coding (CSC) improves sparse coding by learning a s...
10/25/2021

Dictionary Learning Using Rank-One Atomic Decomposition (ROAD)

Dictionary learning aims at seeking a dictionary under which the trainin...
09/09/2017

Convolutional Dictionary Learning

Convolutional sparse representations are a form of sparse representation...
01/26/2023

Learning Large Scale Sparse Models

In this work, we consider learning sparse models in large scale settings...
03/18/2020

Fault Handling in Large Water Networks with Online Dictionary Learning

Fault detection and isolation in water distribution networks is an activ...