Online Convolutional Sparse Coding with Sample-Dependent Dictionary
This work addresses scalability issues in image and signal processing for researchers and practitioners, representing an incremental improvement over existing convolutional sparse coding methods.
The paper tackles the scalability limitations of convolutional sparse coding by introducing a sample-dependent dictionary, where filters are linear combinations of base filters, enabling efficient online learning. Experimental results show the method outperforms existing algorithms with significantly reduced time and space requirements.
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.