Sparse Subspace Clustering Friendly Deep Dictionary Learning for Hyperspectral Image Classification

TL;DR

This paper introduces a deep dictionary learning approach incorporating sparse subspace clustering loss to transform hyperspectral data into a space where subspace clustering is more effective, outperforming existing deep learning methods.

Contribution

It proposes a novel deep dictionary learning framework with SSC loss that enhances hyperspectral image clustering by nonlinear data transformation.

Findings

Improved clustering accuracy over state-of-the-art methods

Effective nonlinear transformation of hyperspectral data

Enhanced subspace separability in transformed space

Abstract

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.