Polarimetric synthetic aperture radar (PolSAR) image interpretation is widely used in various fields. Recently, deep learning has made significant progress in PolSAR image classification. Supervised learning (SL) requires a large amount of labeled PolSAR data with high quality to achieve better performance, however, manually labeled data is insufficient. This causes the SL to fail into overfitting and degrades its generalization performance. Furthermore, the scattering confusion problem is also a significant challenge that attracts more attention. To solve these problems, this article proposes a Heterogeneous Network based Contrastive Learning method(HCLNet). It aims to learn high-level representation from unlabeled PolSAR data for few-shot classification according to multi-features and superpixels. Beyond the conventional CL, HCLNet introduces the heterogeneous architecture for the first time to utilize heterogeneous PolSAR features better. And it develops two easy-to-use plugins to narrow the domain gap between optics and PolSAR, including feature filter and superpixel-based instance discrimination, which the former is used to enhance the complementarity of multi-features, and the latter is used to increase the diversity of negative samples. Experiments demonstrate the superiority of HCLNet on three widely used PolSAR benchmark datasets compared with state-of-the-art methods. Ablation studies also verify the importance of each component. Besides, this work has implications for how to efficiently utilize the multi-features of PolSAR data to learn better high-level representation in CL and how to construct networks suitable for PolSAR data better.
ECP-Mamba: An Efficient Multi-scale Self-supervised Contrastive Learning Method with State Space Model for PolSAR Image Classification
School of Information and Communications Engineering, Xi’an Jiaotong University（西安交通大学信息与通信工程学院）；Department of Mathematics and Fundamental Research, Peng Cheng Laboratory（鹏城实验室数学与基础研究部）；School of Mathematics and Statistics, Xi’an Jiaotong University（西安交通大学数学与统计学院）
Physics-Aware Complex-Valued State Space Model with Scattering-Prior Feature Modulation for PolSAR Image Classification
The College of Information Science and Technology, Beijing University of Chemical Technology（北京化工大学信息科学与技术学院）；The School of Information Science and Engineering, Yunnan University（云南大学信息科学与工程学院）；The Department of Signal Theory and Communications, Polytechnic University of Catalonia（加泰罗尼亚理工大学信号理论与通信系）；The School of Information and Cyberspace Security, Ningxia University（宁夏大学信息与网络空间安全学院）
Weakly-supervised land classification for coastal zone based on deep convolutional neural networks by incorporating dual-polarimetric characteristics into training dataset
S2RC-GCN: A Spatial-Spectral Reliable Contrastive Graph Convolutional Network for Complex Land Cover Classification Using Hyperspectral Images
School of Computer China University of Geosciences Wuhan, China；School of Geography；Information Engineering China University of Geosciences Wuhan, China；School of Management Wuhan University of Science
DI3CL: Contrastive Learning With Dynamic Instances and Contour Consistency for SAR Land-Cover Classification Foundation Model
Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education（教育部智能感知与图像理解重点实验室）；International Research Center for Intelligent Perception and Computation（智能感知与计算国际研究中心）；Joint International Research Laboratory of Intelligent Perception and Computation（智能感知与计算联合国际实验室）；School of Artificial Intelligence, Xidian University（西安电子科技大学人工智能学院）；Hangzhou Institute of Technology（杭州科技学院）
LaCoVL-FER: Landmark-Guided Contrastive Learning Network with Vision-Language Enhancement for Facial Expression Recognition
School of Airspace and Engineering, Shandong University（山东大学航空航天与工程学院）；School of Computer Science and Technology, Shandong University of Finance and Economics（山东财经大学计算机科学与技术学院）；School of Psychology and Neuroscience, University of Glasgow（格拉斯哥大学心理学与神经科学学院）；Faculty of Information Science and Engineering, Ocean University of China（中国海洋大学信息科学与工程学院）
A Multi-Source Data Fusion-based Semantic Segmentation Model for Relic Landslide Detection
Key Lab of Universal Wireless Communication, MOE, Beijing University of Posts and Telecommunications（信息通信领域重点实验室，教育部，北京邮电大学）；China Aero Geophysical Survey and Remote Sensing Center for Natural Resources（中国航空地球物理测绘与遥感自然资源中心）；School of Engineering and Mathematical Sciences, La Trobe University（拉筹伯大学工程与数学科学学院）
MRIFE: A Mask-Recovering and Interactive-Feature-Enhancing Semantic Segmentation Network For Relic Landslide Detection
Beijing University of Posts and Telecommunications（北京邮电大学）；Beijing Institute of Technology（北京理工大学）；China Aero Geophysical Survey and Remote Sensing Center for Natural Resources（中国自然资源航空物探遥感中心）；La Trobe University（拉筹伯大学）
Region Embedding with Intra and Inter-View Contrastive Learning
Nanyang Technological University（南洋理工大学）
无监督区域表示学习旨在从未标记的城市数据中提取密集有效的特征。虽然已经基于多个视图做出了一些努力来解决这个问题，但是现有方法在提取视图中的表示和/或合并来自不同视图的表示方面仍然不足。基于对比学习在表示学习中的成功，我们提出将其用于多视图区域表示学习，并设计了一个称为ReMVC（Region Embedding with Multi-View对比学习）的模型，该模型遵循两个指导原则：i）在每个视图中将区域与其他区域进行比较，以实现有效的表征提取; ii）在不同视图中将区域与自身进行比较，以实现跨视图信息共享。我们设计了视图内对比学习模块和视图间对比学习模块，前者用于学习不同的区域嵌入，后者作为软共正则化器来约束嵌入参数并在多视图间传递知识。我们在两个下游任务中利用学习到的区域嵌入，即土地使用聚类和区域流行度预测。大量的实验表明，我们的模型实现了令人印象深刻的改进相比，七个国家的最先进的基线方法，在土地利用聚类任务的利润率超过30%。
An Iterative Classification and Semantic Segmentation Network for Old Landslide Detection Using High-Resolution Remote Sensing Images
Beijing University of Posts and Telecommunications（北京邮电大学）；Beijing Institute of Technology（北京理工大学）；China Aero Geophysical Survey and Remote Sensing Center for Natural Resources（中国自然资源航空物探遥感中心）；La Trobe University（乐卓博大学）
A multi-temporal multi-spectral attention-augmented deep convolution neural network with contrastive learning for crop yield prediction
Department of Computer Science and Engineering, Indian Institute of Technology (IIT) Indore, Indore 453552, India（计算机科学与工程系，印度理工学院（IIT）印多尔，印多尔453552，印度）
Synth-by-Reg (SbR): Contrastive learning for synthesis-based registration of paired images
University of Sussex（萨塞克斯大学）；Polytechnique Montreal（蒙特利尔理工学院）；Cardiff University（卡迪夫大学）；University College London（伦敦大学学院）；Harvard Medical School（哈佛医学院）；Massachusetts Institute of Technology（麻省理工学院）
Land Use Prediction using Electro-Optical to SAR Few-Shot Transfer Learning
University of Pennsylvania（宾夕法尼亚大学）
卫星图像分析对土地利用、城市化和生态系统监测具有重要意义。深度学习方法可以通过支持不同卫星模式之间的知识转移来弥补个别缺点，从而促进对电光（EO）和合成孔径雷达（SAR）图像等不同卫星模式的分析。最近的进展表明，神经网络嵌入的分布对齐如何通过采用切片Wasserstein距离（SWD）损失来产生强大的迁移学习模型。我们分析了如何将这种方法应用于哨兵-1和-2卫星图像，并开发了几个扩展，使其在实践中有效。在Few-Shot Local Climate Zone（LCZ）预测的应用中，我们证明了这些网络在具有大量类的数据集上优于多个常见基线。此外，我们提供的证据表明，实例规范化可以显着稳定的训练过程，并明确塑造嵌入空间使用监督对比学习可以提高性能。
Habitat Classification from Ground-Level Imagery Using Deep Neural Networks
organization= School of Engineering \& Physical Sciences, University of Lincoln , addressline= Brayford Pool , city= Lincoln , postcode= LN6 7TS , country= United Kingdom；organization= UK Centre for Ecology \& Hydrology , addressline= Lancaster Environment Centre, Library Avenue, Bailrigg , city= Lancaster , postcode= LA1 4AP , country= United Kingdom；organization= UK Centre for Ecology \& Hydrology , addressline= Maclean Building, Benson Lane, Crowmarsh Gifford, Wallingford , city= Oxfordshire , postcode= OX10 8BB , country= United Kingdom；organization= School of Natural Sciences, University of Lincoln , addressline= Brayford Pool , city= Lincoln , postcode= LN6 7TS , country= United Kingdom；organization= Department of Advanced Computing Sciences, Maastricht University , city= Maastricht , postcode= 6229 GS , country= The Netherlands
