NWNingwei Wang

Ningwei Wang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Ningwei Wang has a total of 28 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Complex-Valued Source-Free Domain Adaptation for PolSAR Image Classification

    by Ningwei Wang, Weiqiang Jin, Haixia Bi, Chen Xu, Fan Li

    The discrepancies of sensors, acquisition conditions and terrain class distributions in polarimetric synthetic aperture radar (PolSAR) data has aroused the cross domain PolSAR image classification problem. Domain adaptation, which aims to improve the classification performance of target domain with knowledge from the source domain, is a promising approach to address this issue. However, conventional domain adaptation methods typically assume access to both source and target domain data, which may be infeasible in real-world settings due to data privacy and confidentiality concerns. Therefore, it is crucial to develop source-free domain adaptation PolSAR image classification methods which rely only on target domain data. In this scenario, how to make full use of the label sparse target domain data is a consequent challenge to overcome. To this end, we propose CVSFDA, a complex-valued source-free domain adaptation framework tailored for PolSAR image classification. CVSFDA incorporates a complex-valued multiscale prototypical matching module (CVMP) and a complex-valued relation network (CVRN). Given the pretrained source domain model and the limited labeled samples in target domain, CVMP captures the similarities between samples leveraging the hierarchical spatial information across multiple encoder layers. A similarity convolutional network is further devised in CVRN, to comprehensively model class-specific information in the target domain. Extensive experiments on four benchmark PolSAR datasets demonstrate that CVSFDA achieves superior classification accuracy and generalization ability compared to existing domain adaptation methods.


  • Representation-driven sampling and adaptive policy resetting for improving multi-Agent reinforcement learning

    by Weiqiang Jin, Xingwu Tian, Ningwei Wang, Baohai Wu, Bohang Shi, Biao Zhao, Guang Yang


  • Learning with noisy labels via Mamba and entropy KNN framework

    by Ningwei Wang, Weiqiang Jin, Shirou Jing, Haixia Bi, Guang Yang


  • Open Access

    A Survey on Deep Learning for Few-Shot PolSAR Image Classification

    by Ningwei Wang, Weiqiang Jin, Haixia Bi, Chen Xu, Jinghuai Gao

    Few-shot classification of polarimetric synthetic aperture radar (PolSAR) images is a challenging task due to the scarcity of labeled data and the complex scattering properties of PolSAR data. Traditional deep learning models often suffer from overfitting and catastrophic forgetting in such settings. Recent advancements have explored innovative approaches, including data augmentation, transfer learning, meta-learning, and multimodal fusion, to address these limitations. Data augmentation methods enhance the diversity of training samples, with advanced techniques like generative adversarial networks (GANs) generating realistic synthetic data that reflect PolSAR’s polarimetric characteristics. Transfer learning leverages pre-trained models and domain adaptation techniques to improve classification across diverse conditions with minimal labeled samples. Meta-learning enhances model adaptability by learning generalizable representations from limited data. Multimodal methods integrate complementary data sources, such as optical imagery, to enrich feature representation. This survey provides a comprehensive review of these strategies, focusing on their advantages, limitations, and potential applications in PolSAR classification. We also identify key trends, such as the increasing role of hybrid models combining multiple paradigms and the growing emphasis on explainability and domain-specific customization. By synthesizing SOTA approaches, this survey offers insights into future directions for advancing few-shot PolSAR classification.


  • Open Access

    Self-Distillation-Based Polarimetric Image Classification with Noisy and Sparse Labels

    by Ningwei Wang, Haixia Bi, Fan Li, Chen Xu, Jinghuai Gao

    Polarimetric synthetic aperture radar (PolSAR) image classification, a field crucial in remote sensing, faces significant challenges due to the intricate expertise required for accurate annotation, leading to susceptibility to labeling inaccuracies. Compounding this challenge are the constraints posed by limited labeled samples and the perennial issue of class imbalance inherent in PolSAR image classification. Our research objectives are to address these challenges by developing a novel label correction mechanism, implementing self-distillation-based contrastive learning, and introducing a sample rebalancing loss function. To address the quandary of noisy labels, we proffer a novel label correction mechanism that capitalizes on inherent sample similarities to rectify erroneously labeled instances. In parallel, to mitigate the limitation of sparsely labeled data, this study delves into self-distillation-based contrastive learning, harnessing sample affinities for nuanced feature extraction. Moreover, we introduce a sample rebalancing loss function that adjusts class weights and augments data for small classes. Through extensive experiments on four benchmark PolSAR images, our approach demonstrates its effectiveness in addressing label inaccuracies, limited samples, and class imbalance. Through extensive experiments on four benchmark PolSAR images, our research substantiates the robustness of our proposed methodology, particularly in rectifying label discrepancies in contexts marked by sample paucity and imbalance. The empirical findings illuminate the superior efficacy of our approach, positioning it at the forefront of state-of-the-art PolSAR classification techniques.


  • Open Access

    Reinforced Neighbour Feature Fusion Object Detection with Deep Learning

    by Ningwei Wang, Yaze Li, Hongzhe Liu

    Neural networks have enabled state-of-the-art approaches to achieve incredible results on computer vision tasks such as object detection. However, previous works have tried to improve the performance in various object detection necks but have failed to extract features efficiently. To solve the insufficient features of objects, this work introduces some of the most advanced and representative network models based on the Faster R-CNN architecture, such as Libra R-CNN, Grid R-CNN, guided anchoring, and GRoIE. We observed the performance of Neighbour Feature Pyramid Network (NFPN) fusion, ResNet Region of Interest Feature Extraction (ResRoIE) and the Recursive Feature Pyramid (RFP) architecture at different scales of precision when these components were used in place of the corresponding original members in various networks obtained on the MS COCO dataset. Compared to the experimental results after replacing the neck and RoIE parts of these models with our Reinforced Neighbour Feature Fusion (RNFF) model, the average precision (AP) is increased by 3.2 percentage points concerning the performance of the baseline network.


  • Open Access

    Analysis and Evaluation Methods of Seismic Subsidence Characteristics of Loess and Field Seismic Subsidence

    by Xiaotong Yan, Shun Wang, Ningwei Wang

    The objective of this research is to analyze the dynamic degeneration of loess and the evaluation method of field seismic subsidence. In this study, Q3 loess is taken as the research object, and the dynamic properties of loess with 10%, 20%, 30% and 35% moisture content are tested by triaxial experiment. In addition, seismic subsidence characteristics of loess with dry densities of 1.4g/cm3, 1.6g/cm3, and 1.8g/cm3 and consolidation stress ratios of 1.0, 1.2, 1.4, and 1.6 are analyzed. Then the simplified seismic subsidence estimation method is used to calculate the relationship between seismic subsidence coefficients at different soil depth in one dimensional field, cycle times, and subsidence depth. The results show that the higher the water content of loess is, the greater the change of seismic subsidence appears. The larger the dry density of loess is, the smaller the change degree of seismic subsidence appears. The larger the consolidation stress ratio is, the greater the change of seismic subsidence occurs in loess. When the depth of soil reaches 9.5m, the maximum seismic subsidence coefficient can reach 0.8%. When the depth of soil layer is 10m, the degree of seismic subsidence is the largest. When the depth of soil layer is 12~16m, the settlement depth caused by earthquake subsidence is small. While the depth of soil layer is 8~12m, the settlement degree is large. El objetivo de esta investigación es analizar la dinámica de degeneración de suelos poco compactos y el método de evaluación de subsidencia del campo sísmico. En este estudio, suelos poco compactos tipo Q3 fueron objeto de investigación, y las propiedades dinámicas de estos suelos con 10, 20, 30 y 35 por ciento de contenido de húmedad fueron evaluadas en experimentos triaxiales. Además, se analizaron las características de subsidencia sísmica de los suelos poco compactos con densidades secas de 1.4g/cm3, 1.6g/cm3, y 1.8g/cm3 y un índice de consolidación de esfuerzo de 1.0, 1.2, 1.4 y 1.6. Luego, el método de estimación de la subsidencia sísmica simplificada se utilizó para calcular la relación entre los coeficientes de subsidencia sísmica en diferentes profundidades en un campo dimensional, los tiempos del ciclo y la profundidad de subsidencia. Los resultados muestran que entre más alto sea el contenido de agua en los suelos poco compactos es mayor el cambio de subsidencia sismica. Y que entre mayor sea la densidad seca de estos suelos, más pequeño es el grado de cambio de la subsidencia sísmica. Y, finalmente, cuando el índice de consolidación de esfuerzo es mayor también será mayor el cambio de subsidencia sísmica que ocurre en los suelos poco compactos. Cuando la profundidad del suelo alcanza los 9.5 metros, el coeficiente de subsidencia sísimica puede alcanzar el 0.8 por ciento. Cuando la profundidad de la capa del suelo es de 10 metros, el grado de subsidencia sísmica es mayor. Cuando la profundidad de la capa del suelo es entre 12 y 16 metros, el asentamiento causado por la subsidencia del movimiento de tierra es menor. Mientras la profundidad de la capa del suelo se encuentre entre 8 y 12 metros, el grado de asentamiento es mayor.