This work introduces the entropy momentum pseudo-labeling (EMP) to refine k-means assignments by leveraging entropy-aware confidence and temporal prediction momentum, and utilizes the contextual neighborhood topology (CNT) to exploit the intrinsic geometric structure of the target feature space.
Abstract
Domain adaptation has advanced cross-scene hyperspectral image classification, significantly improving discriminative capability in complex scenarios. However, privacy rules or storage limits often block access to data from the source domain. Conventional domain adaptation methods become impractical, severely restricting their utility in realistic remote sensing scenarios. To tackle this challenge, we propose a topology-aware source-free learning framework. We first introduce the entropy momentum pseudo-labeling (EMP) to refine k-means assignments by leveraging entropy-aware confidence and temporal prediction momentum. Under the guidance of the refined pseudo-labels, we further utilize the contextual neighborhood topology (CNT) to exploit the intrinsic geometric structure of the target feature space. Combining the global structural information extracted by collaborative representation with the local similarity information modeled by nearest neighbor search, the CNT accomplishes the comprehensive encoding of manifold-level geometric properties in the target domain feature space. The overall objective integrates cross-entropy on refined pseudo-labels, log inner product-based topology consistency, and an information-maximization term for balanced classification, ensuring stable adaptation in the source-free setting. Extensive experiments on three typical cross-scenarios demonstrate that the proposed method exceeds state-of-the-art performance, and ablation studies further validate the contribution of each module. The results highlight the critical role of topology-aware modeling in achieving robust and accurate classification without source data.
Few-shot hyperspectral image classification (FS-HSIC) remains highly challenging because the limited number of labeled samples not only makes traditional supervised learning models prone to overfitting but also restricts their ability to learn generalizable spatial–spectral representations. Moreover, existing methods a...
A multisource collaborative framework is presented for cross-domain few-shot HSI classification by coupling meta-learning with diffusion-inspired progressive perturbation, and episodic tasks are constructed from multiple source domains to learn transferable metric structures.
Wen-Xiang Zhu, Jing-Yi Xu, De-Ping Chen et al.· IEEE Transactions on Geoscie...· 0 citations
Under 5-shot evaluation, the best SCRM variants improve OA over the strongest baseline by 2.21 percentage points, which support SCRM as a lightweight supervised strategy for label-scarce hyperspectral image classification.
A neighborhood geometry–guided prototype contrastive adaptation (NGPCA) framework built upon the domain-adversarial neural network is proposed, showing robust performance for cross-domain remote sensing scene classification.
Multi-source cross-domain hyperspectral image (HSI) classification is challenged by heterogeneous sensor configurations, scene-dependent distribution shifts, and limited labeled target data, which hinder effective knowledge transfer across multiple scenes. Motivated by progressive feature correction, we propose a three...
Wen-Xiang Zhu, Jing-Yi Xu, Yong-Xu Liu et al.· Remote Sensing· 0 citations
Hyperspectral image classification (HSIC) has witnessed remarkable progress with the rise of deep learning. Nevertheless, its real-world deployment remains substantially constrained by two fundamental challenges: substantial domain discrepancies across heterogeneous sensors and the scarcity of labeled samples in the re...
Zhi-Yuan Zhang, Jiao-Jiao Li, Rui Song et al.· IEEE Transactions on Image P...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.