Learning Deep Analysis Dictionaries for Image Super-Resolution
arXiv:2001.12010 · doi:10.1109/TSP.2020.3036902
Abstract
Inspired by the recent success of deep neural networks and the recent efforts to develop multi-layer dictionary models, we propose a Deep Analysis dictionary Model (DeepAM) which is optimized to address a specific regression task known as single image super-resolution. Contrary to other multi-layer dictionary models, our architecture contains L layers of analysis dictionary and soft-thresholding operators to gradually extract high-level features and a layer of synthesis dictionary which is designed to optimize the regression task at hand. In our approach, each analysis dictionary is partitioned into two sub-dictionaries: an Information Preserving Analysis Dictionary (IPAD) and a Clustering Analysis Dictionary (CAD). The IPAD together with the corresponding soft-thresholds is designed to pass the key information from the previous layer to the next layer, while the CAD together with the corresponding soft-thresholding operator is designed to produce a sparse feature representation of its input data that facilitates discrimination of key features. DeepAM uses both supervised and unsupervised setup. Simulation results show that the proposed deep analysis dictionary model achieves better performance compared to a deep neural network that has the same structure and is optimized using back-propagation when training datasets are small.
arXiv commentAccepted by IEEE Transactions on Signal Processing
References in corpus (13)
- Adam: A Method for Stochastic Optimization
- On the Number of Linear Regions of Deep Neural Networks
- Convolutional Dictionary Learning: A Comparative Review and New Algorithms
- Deep Neural Networks with Random Gaussian Weights: A Universal Classification Strategy?
- Analysis Operator Learning and Its Application to Image Reconstruction
- Multi-Layer Convolutional Sparse Modeling: Pursuit and Dictionary Learning
- Deep BCD-Net Using Identical Encoding-Decoding CNN Structures for Iterative Image Recovery
- Constrained Overcomplete Analysis Operator Learning for Cosparse Signal Modelling
- Deep Dictionary Learning: A PARametric NETwork Approach
- Convolutional Analysis Operator Learning: Acceleration and Convergence
- Geometric Understanding of Deep Learning
- Learning Filter Bank Sparsifying Transforms
- Convolutional Analysis Operator Learning: Dependence on Training Data