Online Convolutional Sparse Coding with Sample-Dependent Dictionary

2018/04/27 by Yaqing Wang, Wang, Yaqing, Quanming Yao +5
Computer Science · Engineering · #Blind Source Separation Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image and Signal Denoising Methods #Sparse and Compressive Sensing Techniques

paper · pdf · doi:10.48550/arxiv.1804.10366

openalex publication_date 2018/04/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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 convolving with a dictionary shared by all samples, we propose the use of a sample-dependent dictionary in which filters are obtained as linear combinations of a small set of base filters learned from the data. This added flexibility allows a large number of sample-dependent patterns to be captured, while the resultant model can still be efficiently learned by online learning. Extensive experimental results show that the proposed method outperforms existing CSC algorithms with significantly reduced time and space requirements.

Citations

• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• rm K-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation
• Learning the Morphology of Brain Signals Using Alpha-Stable Convolutional Sparse Coding
• Learning Multiple Layers of Features from Tiny Images

Related

• An Efficient Approximate Method for Online Convolutional Dictionary Learning
• Supervised Convolutional Sparse Coding
• Convolutional Dictionary Learning via Local Processing
• Dictionary learning under global sparsity constraint
• Rethinking the CSC Model for Natural Images