Scalable Online Convolutional Sparse Coding
Convolutional sparse coding (CSC) improves sparse coding by learning a shift-invariant dictionary from the data. However, existing CSC algorithms operate in the batch mode and are expensive, in terms of both space and time, on large datasets. In this paper, we alleviate these problems by using online learning. The key is a reformulation of the CSC objective so that convolution can be handled easily in the frequency domain and much smaller history matrices are needed. We use the alternating direction method of multipliers (ADMM) to solve the resulting optimization problem and the ADMM subproblems have efficient closed-form solutions. Theoretical analysis shows that the learned dictionary converges to a stationary point of the optimization problem. Extensive experiments show that convergence of the proposed method is much faster and its reconstruction performance is also better. Moreover, while existing CSC algorithms can only run on a small number of images, the proposed method can handle at least ten times more images.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A Sparse Coding Interpretation of Neural Networks and Theoretical Implications
Neural networks, specifically deep convolutional neural networks, have achieved unprecedented performance in various computer vision tasks, but the rationale for the computations and structures of successful neural netwo…
image-classificationImage ClassificationOnline Convolutional Sparse Coding with Sample-Dependent Dictionary
Convolutional sparse coding (CSC) has been popularly used for the learning of shift-invariant dictionaries in image and signal processing. However, existing methods have limited scalability. In this paper, instead of con…
Efficient ADMM-based Algorithms for Convolutional Sparse Coding
Convolutional sparse coding improves on the standard sparse approximation by incorporating a global shift-invariant model. The most efficient convolutional sparse coding methods are based on the alternating direction met…
Dictionary LearningSparse Coding on Stereo Video for Object Detection
Deep Convolutional Neural Networks (DCNN) require millions of labeled training examples for image classification and object detection tasks, which restrict these models to domains where such datasets are available. In th…
image-classificationImage ClassificationObjectobject-detection+1Optimization Methods for Convolutional Sparse Coding
Sparse and convolutional constraints form a natural prior for many optimization problems that arise from physical processes. Detecting motifs in speech and musical passages, super-resolving images, compressing videos, an…