ASFR-Net: Adversarial Alignment and Spatio-Frequency Refinement Network for Heterogeneous Remote Sensing Image Change Detection

MAIG-Net: Unsupervised Remote Sensing Road Extraction Combining Multi-Layer Adversarial Learning and Intermediate Domain Guidance

MAIG-Net combines a target-label-free ground-sampling-distance rule, an intermediate domain constructed by Fourier domain adaptation (FDA) that transfers only low-frequency target appearance onto labeled source images while preserving the complete source phase and road labels, and Domain-Invariant Feature Alignment modules that perform reliability-weighted, topology-conditioned adversarial alignment at three encoder depths.

Dual-Domain Adversarial Purification for Robust Remote Sensing Scene Classification

Deep learning has boosted remote sensing (RS) scene classification, but adversarial examples can still cause high-confidence misclassification with imperceptible perturbations. Adversarial purification (AP) offers a practical test-time defense without retraining the classifier. However, most existing methods are confined to pixel-space restoration, which may leave residual adversarial effects that persist and amplify through feature extraction, ultimately biasing the prediction. To address these issues, a dual-domain AP (DDAP) framework is proposed to mitigate adversarial effects at both the pixel and feature levels in a unified pipeline. In the pixel domain, a pixel-domain frequency-aware diffusion purification (PFDP) module performs diffusion-based restoration through a frequency-aware dual-stream U-Net (FD-UNet). By integrating adaptive spectral filtering with multidomain consistency constraints, PFDP reduces adversarial-perturbation-dominated high-frequency responses while preserving structural details and semantic information in RS imagery. In the feature domain, an adversarial vulnerable channel dropout (AVCD) strategy models unshifted shallow-feature statistics with a Gaussian mixture model (GMM) and adaptively assigns channelwise dropout probabilities based on a samplewise shift score and channel vulnerability, thereby suppressing residual adversarial influence before downstream classification. Extensive experiments on UC Merced (UCM) and aerial image dataset (AID) across multiple backbones and attack types demonstrate that DDAP consistently improves robustness while maintaining a favorable clean–robust balance compared with representative baselines.

Temporal Variation-Guided Self-Supervised PolSAR Despeckling Network

Abstract. Deep learning–based polarimetric SAR (PolSAR) despeckling faces two main challenges: the scarcity of clean reference images and the difficulty of preserving structural details while suppressing noise. To address these issues, we propose a temporally guided self-supervised network (TGSD-Net), which generates pseudo training pairs from consecutive noisy observations and leverages a change detection–based prior to exploit temporal redundancy and enhance robustness to land-cover changes. TGSD-Net further integrates model and input feature refinements, including auxiliary polarimetric decomposition parameters and a spatiotemporal information fusion module (STIFM) based on a U-Net backbone, to improve temporal and scattering feature representations. The network is specifically designed to robustly handle multi-temporal SAR acquisitions and heterogeneous land-cover types, maintaining consistent scattering structures across different scenes. Extensive experiments on real PolSAR datasets demonstrate that TGSD-Net effectively balances noise suppression with detail preservation. Quantitative metrics, including the equivalent number of looks (ENL) and edge preservation degree (EPD), confirm its superior despeckling performance. Polarimetric decomposition analyses further verify that the network preserves the physical scattering characteristics of PolSAR images.

SCF-Net: A Flow-Guided Alignment-Enhanced SAM–CNN Hybrid Framework for Remote Sensing Change Detection

While integrating convolutional neural networks (CNNs) and the segment anything model (SAM) is promising for remote sensing change detection (CD), effectively synergizing them remains challenging. Existing hybrid methods often rely on simple feature concatenation, failing to bridge the gap between CNNs’ fine-grained local structures and SAM’s global semantic priors. Moreover, neglecting spatial misalignment in bi-temporal imagery often leads to pseudo-changes and boundary inconsistencies. To address these limitations, we propose SCF-Net, a flow-guided alignment-enhanced framework. First, a dual-path fusion module (DPFM) bridges the cross-modal semantic gap by embedding global contexts into local representations. Second, an optical-flow-guided differential enhancement module (OFDEM) implements adaptive flow-based warping to rectify spatial shifts. Finally, a cross-scale fusion module (CSFM) ensures hierarchical feature consistency. Extensive experiments across LEVIR-CD, CLCD, and GFSW-CLCD demonstrate that SCF-Net effectively mitigates granular mismatch and registration noise. The proposed model achieves competitive $F1$ -scores of 91.58%, 81.23%, and 83.80% on the three datasets, respectively, demonstrating its effectiveness and robustness compared to current mainstream algorithms.

CDCCNet: Cross-Domain Consistency-Constrained Domain Generalization Network for Remote Sensing Optical Image Change Detection

Remote sensing change detection (RSCD) aims to identify and localize changes in the same geographical region using bi-temporal or multitemporal images. However, significant feature distribution shifts commonly exist not only between training and real-world data but also between paired images acquired at different times within the same dataset, severely limiting model generalization. Domain-generalized RSCD seeks to learn domain-invariant representations from source domains (seen), enabling direct deployment to target domains (unseen) without requiring target-domain data during training. Existing methods typically attribute performance degradation to style discrepancies and attempt to suppress style variations through feature regularization. However, because style and content information are highly coupled, such strategies often discard critical content representations. In addition, style discrepancies across datasets can further introduce change-domain shifts, which are largely overlooked by existing methods. To address these issues, this article proposes a domain generalization network for RSCD that enables models trained solely on a source domain to generalize effectively to target domains. Specifically, a feature constraint (FC) mechanism is introduced at the encoder stage to mitigate style interference through covariance alignment while preserving essential content information. At the decoder stage, a cross-domain learning (CDL) module is designed to construct a more discriminative embedding space and separate features prone to misclassification. Extensive experiments demonstrate that the proposed method achieves strong robustness and superior detection accuracy across both source and target domains, significantly outperforming existing methods.

Beyond the Clouds: Reliable and Cloud-Aware Spatiotemporal Fusion via Adversarial Regression Wavelets