# When Dictionary Learning Meets Deep Learning: Deep Dictionary Learning and Coding Network for Image Recognition with Limited Data

arXiv: https://arxiv.org/abs/2005.10940 · HTML: https://mlsanity.com/paper/2005.10940/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2020.

## Built on by (most cited first, 11 of 11)

- [Alternative Learning Paradigms for Image Quality Transfer](https://mlsanity.com/paper/2411.05885/) (2024)
- [Sparse Coding with Multi-Layer Decoders using Variance Regularization](https://mlsanity.com/paper/2112.09214/) (2021)
- [SINR: Sparsity Driven Compressed Implicit Neural Representations](https://mlsanity.com/paper/2503.19576/) (2025)
- [Generalization-Memorization Machines](https://mlsanity.com/paper/2207.03976/) (2022)
- [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)
- [Deep Dictionary Learning with An Intra-class Constraint](https://mlsanity.com/paper/2207.06841/) (2022)
- [Evolving Dictionary Representation for Few-shot Class-incremental Learning](https://mlsanity.com/paper/2305.01885/) (2023)
- [Seismic Traveltime Tomography with Label-free Learning](https://mlsanity.com/paper/2402.00310/) (2024)
- [Driving behavior recognition via self-discovery learning](https://mlsanity.com/paper/2503.14194/) (2025)
- [Dictionary-based Pathology Mining with Hard-instance-assisted Classifier Debiasing for Genetic Biomarker Prediction from WSIs](https://mlsanity.com/paper/2603.26809/) (2026)

## Abstract (arXiv)

We present a new Deep Dictionary Learning and Coding Network (DDLCN) for image recognition tasks with limited data. The proposed DDLCN has most of the standard deep learning layers (e.g., input/output, pooling, fully connected, etc.), but the fundamental convolutional layers are replaced by our proposed compound dictionary learning and coding layers. The dictionary learning learns an over-complete dictionary for input training data. At the deep coding layer, a locality constraint is added to guarantee that the activated dictionary bases are close to each other. Then the activated dictionary atoms are assembled and passed to the compound dictionary learning and coding layers. In this way, the activated atoms in the first layer can be represented by the deeper atoms in the second dictionary. Intuitively, the second dictionary is designed to learn the fine-grained components shared among the input dictionary atoms, thus a more informative and discriminative low-level representation of the dictionary atoms can be obtained. We empirically compare DDLCN with several leading dictionary learning methods and deep learning models. Experimental results on five popular datasets show that DDLCN achieves competitive results compared with state-of-the-art methods when the training data is limited. Code is available at https://github.com/Ha0Tang/DDLCN.