In recent years, contrastive learning (CL) methods have achieved remarkable success in few-shot classification of polarimetric synthetic aperture radar (PolSAR) images. However, existing CL models based on Euclidean metric typically vectorize PolSAR data into real-valued or complex-valued vectors with independent channels, disrupting the inherent correlations between polarimetric channels. To address this issue, we propose a novel CL framework, the Riemannian-Euclidean CL network (RECLNet). The proposed RECLNet allows direct input of polarimetric covariance matrices, overcoming the limitations of conventional Euclidean-based CL models that require vectorizing PolSAR data. First, RECLNet constructs hard positive samples by leveraging polarimetric information within the Riemannian space. Second, a series of carefully designed Riemannian manifold operation (RMO) layers are used to extract the Riemannian geometric features of PolSAR data while preserving its matrix structure. Finally, the vision transformer (ViT) is adopted as the backbone of the Euclidean metric encoding to capture contextual information. Experiments conducted on two widely used PolSAR datasets demonstrate that the proposed approach achieves superior performance compared with existing state-of-the-art methods.

Scattering Power Decomposition of polarimetric synthetic aperture radar (PolSAR) coherency matrix is essential for PolSAR image interpretation. However, current research faces two challenges: (1) the contradiction between limited scattering models (i.e. covariance matrix models or coherency matrix models) and the complex, diverse scattering types in reality, leading to incomplete and ambiguous characterization; (2) too many manually configured branches in the solving process due to models having more unknown parameters than observations. To address the above issues, a scattering power decomposition method based on Polarimetric Interferometric Synthetic Aperture Radar (PolInSAR) image and sparse representation theory is proposed. Specifically, to eliminate scattering ambiguity in polarization data, PolInSAR coherence and self-organizing maps (SOM) are introduced to develop unambiguous decomposition schemes. Besides, to enhance the diversity of scattering mechanisms and models, the rotated double-bounce and coherent volume scattering mechanisms for different types of buildings are added; the scattering power decomposition is implemented through sparse representation with an overcomplete dictionary of diverse scattering models. Experiments on three pairs of PolInSAR data validate the effectiveness of the proposed method. This work reveals the essence of the scattering characterization system, offers effective approaches to address its complexities without extensive scattering modeling, and has valuable applications in target detection and fine land cover classification.

Benefiting from the advantages of height sensitivity, the short time span, and the low data cost, interferometric synthetic aperture radar (InSAR) technology has the potential for 3-D reconstruction. However, the layover problem has always been the limitation for the InSAR-based height reconstruction of buildings in complex scenes because of the mixing of scatterings from building facade, roof, and other interferers. In this article, the above layover problem was addressed, and the height reconstruction of buildings in complex scenes was first achieved based on one single interferogram. Specifically, the layover mechanism in complex scenes in the InSAR system was fundamentally explored and was summarized as a general interferometry model. Based on the established model, a height reconstruction method for high-rise buildings was proposed. The main idea is to recognize the facade scattering-dominated area and then reconstruct the complete facade interferometric phase based on the interferometry model and derived facade phase gradient characteristic. Finally, the building height can be obtained based on the phase-height conversation. TerraSAR-X InSAR data in six different complex scenes were used for experiments. For results based on the proposed method, the mean absolute error and root-mean-square error are less than 1.2 m, and compared with the building height reconstruction based on the original layover phase, the accuracy is improved by several meters to tens of meters, indicating that the height reconstruction of buildings in complex scenes can be achieved with high accuracy based on the proposed method.

Polarimetric synthetic aperture radar (PolSAR) target decomposition is an effective way to obtain the scattering mechanism information. However, the problem of volume scattering overestimation in rotated built-up areas has not been completely addressed even with extensive efforts in scattering modeling. The root lies in the scattering ambiguity in polarization response (S matrix, T matrix, and C matrix) which is difficult to remove. To handle this problem, the repeat-pass polarimetric interferometric synthetic aperture radar (PolInSAR) coherence is introduced to PolSAR target decomposition in this article, to distinguish the volume scattering and the scattering generated by rotated dihedral structures and then achieve the volume scattering component correction. Specifically, a building descriptor$P_{bd}$is established based on PolInSAR coherence and then used to distinguish natural and built-up areas before target decomposition. Then, two different scattering model sets, where the volume scattering and the rotated double-bounce scattering do not appear at the same time, are applied in natural and built-up areas, respectively. Applying the above two points to classic decomposition methods, a series of improved methods are proposed, named repeat-pass PolInSAR coherence-assisted target decomposition methods. Experiments on three sets of PolInSAR data confirm the validity of the proposed decomposition methods. Besides, time series PolInSAR data are used to analyze the performance of the algorithm under different temporal baseline conditions. This work may enlighten how to efficiently correct the volume scattering component in rotated built-up areas by introducing repeat-pass PolInSAR coherence into PolSAR target decomposition, to reduce the large amount of energy spent on the complex scattering modeling.

The canopy vertical structure, especially the average height, has always been regarded as an important factor in monitoring forest changes. The coherent scattering model links forest canopy information with radar observations and the random volume over ground (RVoG) model has been extensively applied to the polarimetric SAR interferometry (PolInSAR) data since it was proposed. The complex coherence of the RVoG model was originally derived in a simplified way by neglecting some factors due to the complexity of the scattering process. Thence, this letter proposed a slope three-layer scattering (STLS) model for forest parameters’ estimation in sloping mountain forest region. This model separates the vertical structure of the forest into three layers: the ground layer, the tree-trunk layer, and the canopy layer which account for the simultaneous effects of three scattering components on complex coherence. Moreover, it also corrects the distortion caused by the local terrain slope. The STLS model provides a better understanding of the microwave scattering process in the terrain slope area compared with the traditional RVoG model, S-RVoG model, and general three-layer scattering model (GTLSM) model. Finally, the STLS model has been quantitatively tested with the simulated PolInSAR data with different terrain slopes from PolSARProSim software and qualitatively tested with the spaceborne SIR-C data in Tian-Shan Mount area. The results validate the potential of the proposed STLS model in forest parameter inversion.

Community detection is of great importance for online social network analysis. The volume, variety and velocity of data generated by today's online social networks are advancing the way researchers analyze those networks. For instance, real-world networks, such as Facebook, LinkedIn and Twitter, are inherently growing rapidly and expanding aggressively over time. However, most of the studies so far have been focusing on detecting communities on the static networks. It is computationally expensive to directly employ a well-studied static algorithm repeatedly on the network snapshots of the dynamic networks. We propose DynaMo, a novel modularity-based dynamic community detection algorithm, aiming to detect communities of dynamic networks as effective as repeatedly applying static algorithms but in a more efficient way. DynaMo is an adaptive and incremental algorithm, which is designed for incrementally maximizing the modularity gain while updating the community structure of dynamic networks. In the experimental evaluation, a comprehensive comparison has been made among DynaMo, Louvain (static) and 5 other dynamic algorithms. Extensive experiments have been conducted on 6 real-world networks and 10,000 synthetic networks. Our results show that DynaMo outperforms all the other 5 dynamic algorithms in terms of the effectiveness, and is 2 to 5 times (by average) faster than Louvain algorithm.

Peer-to-peer (P2P) botnets have become one of the major threats in network security for serving as the fundamental infrastructure for various cyber-crimes. More challenges are involved in the problem of detecting P2P botnets, despite a few work claimed to detect centralized botnets effectively. We propose an enhanced PeerHunter, a network-flow level community behavior analysis based system, to detect P2P botnets. Our system starts from a P2P network flow detection component. Then, it uses “mutual contacts” to cluster bots into communities. Finally, it uses network-flow level community behavior analysis to detect potential botnets. In the experimental evaluation, we propose two evasion attacks, where we assume the adversaries know our techniques in advance and attempt to evade our system by making the P2P bots mimic the behavior of legitimate P2P applications. Our results showed that enhanced PeerHunter can obtain high detection rate with few false positives, and high robustness against the proposed attacks.

We present a simple and yet effective approach that can incorporate rationales elicited from annotators into the training of any offthe-shelf classifier.We show that our simple approach is effective for multinomial naïve Bayes, logistic regression, and support vector machines.We additionally present an active learning method tailored specifically for the learning with rationales framework.