|
|
- 2018
基于多任务联合稀疏和低秩表示的高分辨率遥感图像分类
|
Abstract:
多任务学习（multitask learning，MTL）是一种利用多个任务间共享信息并行学习以提高模型泛化性能的机器学习方法，研究表明该方法可以提升高分辨率遥感图像的分类精度。提出一种基于多任务联合稀疏和低秩表示（multitask joint sparse and low-rank representation，MJSLR）的高分辨率遥感图像分类模型，并采用加速近似梯度法求解凸的光滑函数和非光滑约束的组合优化问题。实验对比分析了多任务和单任务的学习模型，并比较了MJSLR、多核学习方法和多任务联合稀疏表达方法的图像分类准确率，结果表明多任务学习模型能够获得优于单任务学习模型的分类精度，而且融合低秩约束能够一定程度上提高多任务分类模型的精度
| [1] | Zhang C, Liu J, Tian Q, et al. Image Classification by Non-negative Sparse Coding, Low-rank and Sparse Decomposition[C]. IEEE Computer Vision and Pattern Recognition,Colorado Springs,USA, 2011 |
| [2] | Lin Y, Liu T, Fuh C. Local Ensemble Kernel Learning for Object Category Recognition[C]. IEEE International Conference on Computer Vision, Rio de Janeiro, Brazil, 2007 |
| [3] | Nesterov Y. Introductory Lectures on Convex Optimization:A Basic Course[M]. New York:Kluwer Academic Publishers, 2004 |
| [4] | Beck A, Teboulle M. A Fast Iterative Shrinkage-thresholding Algorithm for Linear Inverse Problems[J]. <em>SIAM Journal on Imaging Sciences, </em>2009, 2(1):183-202 |
| [5] | Mei S, Cao B, Sun J. Encoding Low-Rank and Sparse Structures Simultaneously in Multi-task Learning[J]. Microsoft Technical Report, 2012,124(1):1-16 |
| [6] | Ji S, Ye J. An Accelerated Gradient Method for Trace Norm Minimization[C]. The 26th Annual International Conference on Machine Learning,Montreal, Canada,2009 |
| [7] | Chen X, Pan W, Kwok J T, et al. Accelerated Gradient Method for Multi-task Sparse Learning Problem[C]. The 9th IEEE International Conference on Data Mining, Las Vegas,USA, 2009 |
| [8] | Lazebnik S, Schmid C, Ponce J. Beyond Bags of Features:Spatial Pyramid Matching for Recognizing Natural Scene Categories[C]. IEEE Computer Vision and Pattern Recognition, New York,USA, 2006 |
| [9] | Shechtman E, Irani M. Matching Local Self-similarities Across Images and Videos[C]. IEEE Conference on Computer Vision and Pattern Recognition,Minneapolis, USA, 2007 |
| [10] | GoelP K, PrasherS O, PatelR M, et al. Classification of Hyperspectral Data by Decision Trees and Artificial Neural Networks to Identify Weed Stress and Nitrogen Status of Corn[J].<em> Computers and Electronics in Agriculture</em>, 2003,39(2):67-93 |
| [11] | Qi K, Wu H, Shen C, et al. Land-Use Scene Classification in High-Resolution Remote Sensing Images Using Improved Correlatons[J]. <em>IEEE Geoscience and Remote Sensing Letters,</em> 2015,12(12):2403-2407 |
| [12] | Zhang Q, Huang X, Zhang L. Multiscale Images Segmentation and Classification with Supervised ECHO of High Spatial Resolution Remotely Sensed Imagery[J]. <em>Geomatics and Information Science of Wuhan University, </em>2011, 36(1):117-121(张倩, 黄昕, 张良培. 多尺度同质区域提取的高分辨率遥感影像分类研究[J]. 武汉大学学报·信息科学版,2011, 36(1):117-121) |
| [13] | Berg A C, Malik J. Geometric Blur for Template Matching[C]. IEEE Computer Vision and Pattern Recognition, Hawaii,USA, 2001 |
| [14] | Pu Jian. On Multitask Learning Methods[D]. Shanghai:Fudan University, 2013(浦剑. 多任务学习算法研究[D]. 上海:复旦大学, 2013) |
| [15] | Yuan X, Liu X,Yan S. Visual Classification with Multitask Joint Sparse Representation[J]. <em>IEEE Transactions on Image Processing, </em>2012,21(10):4349-4360 |
| [16] | Leiva-MurilloJ M, Gómez-Chova L, Camps-Valls G. Multitask Remote Sensing Data Classification[J]. <em>IEEE Transactions on Geoscience &Remote Sensing, </em>2013,51(1):151-161 |
| [17] | Yu Binfeng.Multitask LearningandIts Application in Spectral Multivariate Calibration[D]. Hefei:University of Science and Technology of China, 2015(俞斌峰. 多任务学习及其在光谱数据分析中的应用[D].合肥:中国科学技术大学,2015) |
| [18] | Zhang T, Ghanem B, Liu B, et al.Low-Rank Sparse Coding for Image Classification[C]. IEEE International Conference on Computer Vision,Sydney, Australia, 2013 |
| [19] | Obozinski G, Taskar B, Jordan M. Joint Covariate Selection and Joint Subspace Selection for Multiple Classification Problems[J]. <em>Statistics and Computing,</em> 2009, 20(2):231-252 |
| [20] | Chen J,Zhou J, Ye J. Integrating Low-rank and Group-sparse Structures for Robust Multi-task Learning[C]. International Conference on Knowledge Discovery and Data Mining,San Diego, USA, 2011 |
| [21] | Yang Y, Newsam S. Bag-of-visual-words and Spatial Extensions for Land-use Classification[C]. The 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems, San Jose,USA, 2010 |
| [22] | Eismann M T, Stocker A D, Nasrabadi N M. Automated Hyperspectral Cueing for Civilian Search and Rescue[J]. <em>Proceedings of IEEE, </em>2009, 97(6):1031-1055 |
| [23] | Iordache M D, Bioucas-DiasJ M, Plaza A. Sparse Unmixing of Hyperspectral Data[J]. IEEE Transactions Geoscience and Remote Sensing, 2011,49(6):2014-2039 |
| [24] | Cheng Shiyao, Mei Tiancan, Liu Guoying. Application of Multi-level MRF Using Structural Feature to Remote Sensing Image Classification[J]. <em>Geomatics and Information Science of Wuhan University,</em> 2015, 40(9):1180-1187(程诗尧, 梅天灿, 刘国英. 顾及结构特征的多层次马尔科夫随机场模型在影像分类中的应用[J]. 武汉大学学报·信息科学版,2015, 40(9):1180-1187) |
| [25] | Xu Kan, Yang Wen, Chen Lijun, et al. Satellite Image Scene Categorization Based on Topic Models[J]. <em>Geomatics and Information Science of Wuhan University, </em>2011, 36(5):540-543(徐侃,杨文,陈丽君,等. 利用主题模型的遥感图像场景分类[J]. 武汉大学学报·信息科学版, 2011, 36(5):540-543) |
| [26] | Caruana R. Multitask Learning[J]. <em>Machine Learning,</em> 1997, 28(1):41-75 |
| [27] | Wright J, Yang A Y, Ganesh A, et al. Robust Face Recognition via Sparse Representation[J].i> IEEE Transactions on Pattern Analysis and Machine Intelligence<, 2009, 31(2):210-227 |
