# Sparse Subspace Clustering Friendly Deep Dictionary Learning for Hyperspectral Image Classification

arXiv: https://arxiv.org/abs/2111.13920 · HTML: https://mlsanity.com/paper/2111.13920/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 17 references that are in the map.
- First posted on arXiv 27 Nov 2021.

## Builds on (most cited first, 6 of 6)

- [Deep Dictionary Learning: A PARametric NETwork Approach](https://mlsanity.com/paper/1803.04022/) (2018)
- [Unsupervised Segmentation of Hyperspectral Images Using 3D Convolutional Autoencoders](https://mlsanity.com/paper/1907.08870/) (2019)
- [When Dictionary Learning Meets Deep Learning: Deep Dictionary Learning and Coding Network for Image Recognition with Limited Data](https://mlsanity.com/paper/2005.10940/) (2020)
- [Deep Clustering With Intra-class Distance Constraint for Hyperspectral Images](https://mlsanity.com/paper/1904.00562/) (2019)
- [Discriminative Robust Deep Dictionary Learning for Hyperspectral Image Classification](https://mlsanity.com/paper/1912.10803/) (2019)
- [Row-Sparse Discriminative Deep Dictionary Learning for Hyperspectral Image Classification](https://mlsanity.com/paper/1912.10804/) (2019)

## Built on by (most cited first, 1 of 1)

- [Deep Dictionary Learning with An Intra-class Constraint](https://mlsanity.com/paper/2207.06841/) (2022)

## Abstract (arXiv)

Subspace clustering techniques have shown promise in hyperspectral image segmentation. The fundamental assumption in subspace clustering is that the samples belonging to different clusters/segments lie in separable subspaces. What if this condition does not hold? We surmise that even if the condition does not hold in the original space, the data may be nonlinearly transformed to a space where it will be separable into subspaces. In this work, we propose a transformation based on the tenets of deep dictionary learning (DDL). In particular, we incorporate the sparse subspace clustering (SSC) loss in the DDL formulation. Here DDL nonlinearly transforms the data such that the transformed representation (of the data) is separable into subspaces. We show that the proposed formulation improves over the state-of-the-art deep learning techniques in hyperspectral image clustering.