# Deep Dictionary Learning: A PARametric NETwork Approach

arXiv: https://arxiv.org/abs/1803.04022 · HTML: https://mlsanity.com/paper/1803.04022/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Mar 2018.

## Built on by (most cited first, 12 of 12)

- [Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models](https://mlsanity.com/paper/2502.12892/) (2025)
- [Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment](https://mlsanity.com/paper/2502.03714/) (2025)
- [Phase Collapse in Neural Networks](https://mlsanity.com/paper/2110.05283/) (2021)
- [Sparse Coding with Multi-Layer Decoders using Variance Regularization](https://mlsanity.com/paper/2112.09214/) (2021)
- [Deep Transform and Metric Learning Networks](https://mlsanity.com/paper/2104.10329/) (2021)
- [Deep learning based dictionary learning and tomographic image reconstruction](https://mlsanity.com/paper/2108.11730/) (2021)
- [Sparse Subspace Clustering Friendly Deep Dictionary Learning for Hyperspectral Image Classification](https://mlsanity.com/paper/2111.13920/) (2021)
- [Lightweight Conceptual Dictionary Learning for Text Classification Using Information Compression](https://mlsanity.com/paper/2405.01584/) (2024)
- [Boosting Adversarial Robustness and Generalization with Dictionary Structure](https://mlsanity.com/paper/2502.00834/) (2025)
- [Evolving Dictionary Representation for Few-shot Class-incremental Learning](https://mlsanity.com/paper/2305.01885/) (2023)
- [Deep State-Space Model for Predicting Cryptocurrency Price](https://mlsanity.com/paper/2311.14731/) (2023)
- [Seismic Traveltime Tomography with Label-free Learning](https://mlsanity.com/paper/2402.00310/) (2024)

## Abstract (arXiv)

Deep dictionary learning seeks multiple dictionaries at different image scales to capture complementary coherent characteristics. We propose a method for learning a hierarchy of synthesis dictionaries with an image classification goal. The dictionaries and classification parameters are trained by a classification objective, and the sparse features are extracted by reducing a reconstruction loss in each layer. The reconstruction objectives in some sense regularize the classification problem and inject source signal information in the extracted features. The performance of the proposed hierarchical method increases by adding more layers, which consequently makes this model easier to tune and adapt. The proposed algorithm furthermore, shows remarkably lower fooling rate in presence of adversarial perturbation. The validation of the proposed approach is based on its classification performance using four benchmark datasets and is compared to a CNN of similar size.