# Joint Learning of Discriminative Low-dimensional Image Representations Based on Dictionary Learning and Two-layer Orthogonal Projections

## TL;DR

This paper proposes a joint learning framework that combines dictionary learning and two-layer orthogonal projections to obtain discriminative low-dimensional image representations, aiming to improve image classification performance.

## Contribution

It introduces a novel joint learning method integrating dictionary learning with two-layer orthogonal projections for better image feature extraction.

## Key findings

- Enhanced discriminative power of image representations
- Improved classification accuracy on benchmark datasets
- Effective dimensionality reduction with preserved discriminability

## Abstract

There are some inadequacies in the language description of this paper that require further improvement. This paper is based on a revision of a conference paper. It is now necessary to further explain the difference between the contributions of the two papers.

---
Source: https://tomesphere.com/paper/1903.09977