Hyperspectral unmixing (HU) plays a fundamental role in a wide range of hyperspectral applications. It is still challenging due to the common presence of outlier channels and the large solution space. To address the above two issues, we propose a novel model by emphasizing both robust representation and learning-based sparsity. Specifically, we apply the $\ell_{2,1}$-norm to measure the representation error, preventing outlier channels from dominating our objective. In this way, the side effects of outlier channels are greatly relieved. Besides, we observe that the mixed level of each pixel varies over image grids. Based on this observation, we exploit a learning-based sparsity method to simultaneously learn the HU results and a sparse guidance map. Via this guidance map, the sparsity constraint in the $\ell_{p}\!\left(\!0\!<\! p\!\leq\!1\right)$-norm is adaptively imposed according to the learnt mixed level of each pixel. Compared with state-of-the-art methods, our model is better suited to the real situation, thus expected to achieve better HU results. The resulted objective is highly non-convex and non-smooth, and so it is hard to optimize. As a profound theoretical contribution, we propose an efficient algorithm to solve it. Meanwhile, the convergence proof and the computational complexity analysis are systematically provided. Extensive evaluations verify that our method is highly promising for the HU task---it achieves very accurate guidance maps and much better HU results compared with state-of-the-art methods.
Adaptive Multi-Order Graph Regularized NMF with Dual Sparsity for Hyperspectral Unmixing
School of Automation Engineering, Shanghai University of Electric Power（上海电力大学自动化工程学院）；School of Mechatronic Engineering and Automation, Shanghai University（上海大学机械电子工程与自动化学院）；School of Intelligent Systems Engineering, Sun Yat-sen University（中山大学智能系统工程学院）
A General Framework for Group Sparsity in Hyperspectral Unmixing Using Endmember Bundles
Department of Mathematics, Michigan State University（数学系，密歇根州立大学）；Department of Mathematics and the School of Data Science and Society, The University of North Carolina at Chapel Hill（数学系和数据科学与社会学院，北卡罗来纳大学教堂山分校）；Department of Mathematics and the Department of Computational Mathematics, Science and Engineering, Michigan State University（数学系和计算数学、科学与工程系，密歇根州立大学）
A Generalized Multiscale Bundle-Based Hyperspectral Sparse Unmixing Algorithm
Universidade Federal de Santa Catarina（圣卡塔琳娜联邦大学）；Université de Lorraine（洛林大学）；CNRS（法国国家科学研究中心）；CRAN（CRAN 研究中心）；Universidade Católica de Pelotas（佩洛塔斯天主教大学）
Correntropy Maximization via ADMM - Application to Robust Hyperspectral Unmixing
Institut Charles Delaunay (CNRS), Université de Technologie de Troyes（特鲁瓦技术大学，夏尔·德洛内研究所（法国国家科学研究中心））；School of Engineering and Physical Sciences, Heriot-Watt University（赫瑞瓦特大学，工程与物理科学学院）；LITIS lab, Université de Rouen（鲁昂大学，LITIS实验室）
Department of Engineering Cybernetics, Norwegian University of Science and Technology（工程 cybernetics 部，挪威科学与技术大学）；Department of Biology, Norwegian University of Science and Technology（生物学部，挪威科学与技术大学）；Department of Automatic Control and Systems Engineering, University Politehnica Bucharest（自动控制与系统工程部，布加勒斯特理工大学）
Transformer-Guided Content-Adaptive Graph Learning for Hyperspectral Unmixing
School of Automation Engineering, Shanghai University of Electric Power（上海电力大学自动化工程学院）；School of Mechatronic Engineering and Automation, Shanghai University（上海大学机电工程与自动化学院）；School of Intelligent Systems Engineering, Sun Yat-sen University（中山大学智能系统工程学院）
Extending the Unmixing methods to Multispectral Images
Universite Bourgogne Franche-Comté（勃艮第-弗朗什-孔泰大学）；Le Centre de Recherche et de Restauration des Musées de France（法国博物馆研究与修复中心）；Centre National de la Recherche Scientifique（法国国家科学研究中心）
End-to-End Unmixing with Material Prompts for Hyperspectral Object Tracking
School of Information and Communication Technology, Griffith University, Australia（信息与通信技术学院，格里菲斯大学，澳大利亚）；School of Engineering and Built Environment, Griffith University, Australia（工程与建筑环境学院，格里菲斯大学，澳大利亚）；School of Environment and Science, Griffith University, Australia（环境与科学学院，格里菲斯大学，澳大利亚）
WS-Net: Weak-Signal Representation Learning and Gated Abundance Reconstruction for Hyperspectral Unmixing via State-Space and Weak Signal Attention Fusion
School of Information and Communication Technology, Griffith University（信息与通信技术学院，格里菲斯大学）；School of Computing, Engineering and Mathematical Sciences, La Trobe University（计算、工程与数学科学学院，拉特罗布大学）；CSIRO Agriculture and Food（澳大利亚农业与食品CSIRO）
本报告涉及使用稀疏信号表示和稀疏错误校正的自动人脸识别技术。最近对这些技术的兴趣大部分来自Wright等人（2009）的论文“Robust Face Recognition via Sparse Representation”，其示出了在某些技术条件下，如何可以将面部识别问题转换为在训练图像和各个像素的图像的“字典”方面寻求给定输入面部图像的稀疏表示的问题。在这份报告中，我们试图澄清一些经常遇到的问题，这项工作，特别是使用稀疏表示技术的人脸识别的有效性。
ADJUST: A Dictionary-Based Joint Reconstruction and Unmixing Method for Spectral Tomography
Centrum Wiskunde & Informatica（数学与计算机科学中心）；University of Antwerp（安特卫普大学）；Utrecht University（乌得勒支大学）；Leiden Institute of Advanced Computer Science（莱顿大学高级计算机科学研究所）
Robust retrieval of material chemical states in X-ray microspectroscopy
Southern University of Science and Technology（南方科技大学）；National Centre for Applied Mathematics Shenzhen（深圳国家应用数学中心）；City University of Hong Kong（香港城市大学）
Euclidean Distance to Convex Polyhedra and Application to Class Representation in Spectral Images
Center for Mathematical Morphology (CMM), Mines Paris, PSL University（巴黎矿业学院 数学形态学中心（CMM），PSL大学）；Laboratoire de Réactivité et Chimie des Solides (LRCS), CNRS UMR 7314, Université de Picardie Jules Verne（皮卡第儒勒·凡尔纳大学 固体反应性与化学实验室（LRCS），法国国家科研中心UMR 7314）
An Integrated Approach to Produce Robust Models with High Efficiency
University of California, Irvine（加州大学欧文分校）；The University of Utah（犹他大学）
深度神经网络（DNN）需要在实际应用中既高效又健壮。量化和结构简化是使DNN适应移动设备的有前途的方法，而对抗训练是使DNN健壮的最流行的方法。在这项工作中，我们试图通过将收敛的松弛量化算法Binary-Relax（BR）应用于一个强大的对抗训练模型ResNets Ensemble via Feynman-Kac Formalism（EnResNet）来获得这两个特征。我们还发现，高精度，如三进制（tnn）和4位，量化将产生稀疏DNN。然而，这种稀疏性在对抗训练下是非结构化的。为了解决对抗性训练影响DNN在干净图像上的准确性和稀疏性结构的问题，我们设计了一个折衷的损失函数，帮助DNN保持其自然的准确性和提高信道稀疏性。通过我们的折衷损失函数，我们实现了两个目标，在弱攻击下不降低抵抗力，在强攻击下只降低很小的抵抗力。与具有权衡损失函数的量化EnResNet一起，我们提供了具有高效率的鲁棒模型。
