Dual-stage Hyperspectral Image Classification Model with Spectral Supertoken

TL;DR

This paper introduces DSTC, a dual-stage hyperspectral image classifier that uses spectral supertokens and soft labels to improve pixel classification accuracy and boundary precision, addressing spectral correlation challenges.

Contribution

The paper presents a novel dual-stage hyperspectral classification model utilizing spectral supertokens and adaptive soft labels, enhancing accuracy and boundary delineation over existing methods.

Findings

Demonstrates robust classification on multiple datasets.

Effective management of spectral variations and class imbalance.

Code will be publicly available for reproducibility.

Abstract

Hyperspectral image classification, a task that assigns pre-defined classes to each pixel in a hyperspectral image of remote sensing scenes, often faces challenges due to the neglect of correlations between spectrally similar pixels. This oversight can lead to inaccurate edge definitions and difficulties in managing minor spectral variations in contiguous areas. To address these issues, we introduce the novel Dual-stage Spectral Supertoken Classifier (DSTC), inspired by superpixel concepts. DSTC employs spectrum-derivative-based pixel clustering to group pixels with similar spectral characteristics into spectral supertokens. By projecting the classification of these tokens onto the image space, we achieve pixel-level results that maintain regional classification consistency and precise boundary. Moreover, recognizing the diversity within tokens, we propose a class-proportion-based soft label. This label adaptively assigns weights to different categories based on their prevalence, effectively managing data distribution imbalances and enhancing classification performance. Comprehensive experiments on WHU-OHS, IP, KSC, and UP datasets corroborate the robust classification capabilities of DSTC and the effectiveness of its individual components. Code will be publicly available at https://github.com/laprf/DSTC.