Exploring Multi-Timestep Multi-Stage Diffusion Features for Hyperspectral Image Classification

TL;DR

This paper introduces MTMSD, a novel diffusion-based framework that leverages multi-timestep multi-stage features for hyperspectral image classification, significantly improving accuracy by exploiting rich contextual information.

Contribution

The paper proposes the first framework to utilize multi-timestep multi-stage diffusion features in hyperspectral image classification, enhancing feature richness and classification performance.

Findings

Outperforms state-of-the-art methods on four public datasets.

Achieves notable accuracy improvements on the challenging Houston 2018 dataset.

Demonstrates effective feature purification and adaptive feature fusion strategies.

Abstract

The effectiveness of spectral-spatial feature learning is crucial for the hyperspectral image (HSI) classification task. Diffusion models, as a new class of groundbreaking generative models, have the ability to learn both contextual semantics and textual details from the distinct timestep dimension, enabling the modeling of complex spectral-spatial relations in HSIs. However, existing diffusion-based HSI classification methods only utilize manually selected single-timestep single-stage features, limiting the full exploration and exploitation of rich contextual semantics and textual information hidden in the diffusion model. To address this issue, we propose a novel diffusion-based feature learning framework that explores Multi-Timestep Multi-Stage Diffusion features for HSI classification for the first time, called MTMSD. Specifically, the diffusion model is first pretrained with unlabeled HSI patches to mine the connotation of unlabeled data, and then is used to extract the multi-timestep multi-stage diffusion features. To effectively and efficiently leverage multi-timestep multi-stage features,two strategies are further developed. One strategy is class & timestep-oriented multi-stage feature purification module with the inter-class and inter-timestep prior for reducing the redundancy of multi-stage features and alleviating memory constraints. The other one is selective timestep feature fusion module with the guidance of global features to adaptively select different timestep features for integrating texture and semantics. Both strategies facilitate the generality and adaptability of the MTMSD framework for diverse patterns of different HSI data. Extensive experiments are conducted on four public HSI datasets, and the results demonstrate that our method outperforms state-of-the-art methods for HSI classification, especially on the challenging Houston 2018 dataset.