Multisource Collaborative Domain Generalization for Cross-Scene Remote Sensing Image Classification

doi:10.1109/TGRS.2024.3478385

Multisource Collaborative Domain Generalization for Cross-Scene Remote Sensing Image Classification

2024-01-01

2

PRE

AI

DOI：10.1109/TGRS.2024.3478385

Original

Original request for help

Save

Abstract

En 中文

Cross-scene image classification aims to transfer prior knowledge of ground materials to annotate regions with different distributions and reduce hand-crafted cost in the field of remote sensing. However, existing approaches focus on single-source domain (SD) generalization to unseen target domains (TDs), and are easily confused by large real-world domain shifts due to the limited training information and insufficient diversity modeling capacity. To address this gap, we propose a novel multisource collaborative domain generalization (MS-CDG) framework based on homogeneity and heterogeneity characteristics of multisource (MS) remote sensing data, which considers data-aware adversarial augmentation and model-aware multilevel diversification simultaneously to enhance cross-scene generalization performance. The data-aware adversarial augmentation adopts an adversary neural network with semantic guide to generate MS samples by adaptively learning realistic channel and distribution changes across domains. In views of cross-domain (CD) and intra-domain (ID) modeling, the model-aware diversification transforms the shared spatial-channel features of MS data into the class-wise prototype and kernel mixture module, to address domain discrepancies and cluster different classes effectively. Finally, the joint classification of original and augmented MS samples is employed by introducing a distribution consistency alignment to increase model diversity and ensure better domain-invariant representation learning. Extensive experiments on three public MS remote sensing datasets demonstrate the superior performance of the proposed method when benchmarked with the state-of-the-art methods.

Keywords:

Remote sensing

Data models

Image classification

Training

Semantics

Feature extraction

Data augmentation

Sensors

Imaging

Predictive models

Cross scene

domain generalization (DG)

image classification

multisource (MS) data

remote sensing

Multisource Collaborative Domain Generalization for Cross-Scene Remote Sensing Image Classification

Abstract

Journal

Organization