# Superpixel-guided Discriminative Low-rank Representation of Hyperspectral Images for Classification

arXiv: https://arxiv.org/abs/2108.11172 · HTML: https://mlsanity.com/paper/2108.11172/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 52 references that are in the map.
- First posted on arXiv 25 Aug 2021.

## Builds on (most cited first, 5 of 5)

- [Hybrid Noise Removal in Hyperspectral Imagery With a Spatial-Spectral Gradient Network](https://mlsanity.com/paper/1810.00495/) (2018)
- [Locality and Structure Regularized Low Rank Representation for Hyperspectral Image Classification](https://mlsanity.com/paper/1905.02488/) (2019)
- [Accelerating ADMM for Efficient Simulation and Optimization](https://mlsanity.com/paper/1909.00470/) (2019)
- [On the Global Linear Convergence of the ADMM with Multi-Block Variables](https://mlsanity.com/paper/1408.4266/) (2014)
- [Global Convergence of Unmodified 3-Block ADMM for a Class of Convex Minimization Problems](https://mlsanity.com/paper/1505.04252/) (2015)

## Built on by (most cited first, 4 of 4)

- [Binary Change Guided Hyperspectral Multiclass Change Detection](https://mlsanity.com/paper/2112.04493/) (2021)
- [Irregular Tensor Low-Rank Representation for Hyperspectral Image Representation](https://mlsanity.com/paper/2410.18388/) (2024)
- [Probabilistic Deep Metric Learning for Hyperspectral Image Classification](https://mlsanity.com/paper/2211.08349/) (2022)
- [Structural-Spectral Graph Convolution with Evidential Edge Learning for Hyperspectral Image Clustering](https://mlsanity.com/paper/2506.09920/) (2025)

## Abstract (arXiv)

In this paper, we propose a novel classification scheme for the remotely sensed hyperspectral image (HSI), namely SP-DLRR, by comprehensively exploring its unique characteristics, including the local spatial information and low-rankness. SP-DLRR is mainly composed of two modules, i.e., the classification-guided superpixel segmentation and the discriminative low-rank representation, which are iteratively conducted. Specifically, by utilizing the local spatial information and incorporating the predictions from a typical classifier, the first module segments pixels of an input HSI (or its restoration generated by the second module) into superpixels. According to the resulting superpixels, the pixels of the input HSI are then grouped into clusters and fed into our novel discriminative low-rank representation model with an effective numerical solution. Such a model is capable of increasing the intra-class similarity by suppressing the spectral variations locally while promoting the inter-class discriminability globally, leading to a restored HSI with more discriminative pixels. Experimental results on three benchmark datasets demonstrate the significant superiority of SP-DLRR over state-of-the-art methods, especially for the case with an extremely limited number of training pixels.