Enhancing Knowledge Transfer in Hyperspectral Image Classification via Cross-scene Knowledge Integration

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Huo, Lu, Huang, Wenjian, Zhang, Jianguo, Xu, Min, Zhang, Haimin
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917135790374912
author Huo, Lu
Huang, Wenjian
Zhang, Jianguo
Xu, Min
Zhang, Haimin
author_facet Huo, Lu
Huang, Wenjian
Zhang, Jianguo
Xu, Min
Zhang, Haimin
contents Knowledge transfer has strong potential to improve hyperspectral image (HSI) classification, yet two inherent challenges fundamentally restrict effective cross-domain transfer: spectral variations caused by different sensors and semantic inconsistencies across heterogeneous scenes. Existing methods are limited by transfer settings that assume homogeneous domains or heterogeneous scenarios with only co-occurring categories. When label spaces do not overlap, they further rely on complete source-domain coverage and therefore overlook critical target-private information. To overcome these limitations and enable knowledge transfer in fully heterogeneous settings, we propose Cross-scene Knowledge Integration (CKI), a framework that explicitly incorporates target-private knowledge during transfer. CKI includes: (1) Alignment of Spectral Characteristics (ASC) to reduce spectral discrepancies through domain-agnostic projection; (2) Cross-scene Knowledge Sharing Preference (CKSP), which resolves semantic mismatch via a Source Similarity Mechanism (SSM); and (3) Complementary Information Integration (CII) to maximize the use of target-specific complementary cues. Extensive experiments verify that CKI achieves state-of-the-art performance with strong stability across diverse cross-scene HSI scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2512_08989
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing Knowledge Transfer in Hyperspectral Image Classification via Cross-scene Knowledge Integration
Huo, Lu
Huang, Wenjian
Zhang, Jianguo
Xu, Min
Zhang, Haimin
Computer Vision and Pattern Recognition
Knowledge transfer has strong potential to improve hyperspectral image (HSI) classification, yet two inherent challenges fundamentally restrict effective cross-domain transfer: spectral variations caused by different sensors and semantic inconsistencies across heterogeneous scenes. Existing methods are limited by transfer settings that assume homogeneous domains or heterogeneous scenarios with only co-occurring categories. When label spaces do not overlap, they further rely on complete source-domain coverage and therefore overlook critical target-private information. To overcome these limitations and enable knowledge transfer in fully heterogeneous settings, we propose Cross-scene Knowledge Integration (CKI), a framework that explicitly incorporates target-private knowledge during transfer. CKI includes: (1) Alignment of Spectral Characteristics (ASC) to reduce spectral discrepancies through domain-agnostic projection; (2) Cross-scene Knowledge Sharing Preference (CKSP), which resolves semantic mismatch via a Source Similarity Mechanism (SSM); and (3) Complementary Information Integration (CII) to maximize the use of target-specific complementary cues. Extensive experiments verify that CKI achieves state-of-the-art performance with strong stability across diverse cross-scene HSI scenarios.
title Enhancing Knowledge Transfer in Hyperspectral Image Classification via Cross-scene Knowledge Integration
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.08989