2017年12月第一周推荐文章

  1. Recursive Autoencoders-Based Unsupervised Feature Learning for Hyperspectral Image Classification
  2. Weighted Low-Rank Representation-Based Dimension Reduction for Hyperspectral Image Classification
  3. Fast Spectral Clustering With Anchor Graph for Large Hyperspectral Images
  4. Constrained Band Subset Selection for Hyperspectral Imagery
  5. Unsupervised Band Selection Using Block-Diagonal Sparsity for Hyperspectral Image Classification
  6. A New Unsupervised Hyperspectral Band Selection Method Based on Multiobjective Optimization
  7. Hyperspectral Image Classification via Low-Rank and Sparse Representation With Spectral Consistency
    Constraint
  8. Multiscale Superpixel-Level Subspace-Based Support Vector Machines for Hyperspectral Image Classification
  9. Weight-Based Rotation Forest for Hyperspectral Image Classification

海冰分类:
Sea Ice Classification Using Cryosat-2 Altimeter Data by Optimal Classifier–Feature Assembly

2017年12月 IEEE TGRS 推荐文章

1. Multimorphological Superpixel Model for Hyperspectral Image Classification

With the development of hyperspectral sensors, nowadays, we can easily acquire large amount of hyperspectral images (HSIs) with very high spatial resolution, which has led to a better identification of relatively small structures. Owing to the high spatial resolution, there are much less mixed pixels in the HSIs, and the boundaries between these categories are much clearer. However, the high spatial resolution also leads to complex and fine geometrical structures and high inner-class variability, which make the classification results very ``noisy.'' In this paper, we propose a multimorphological superpixel (MMSP) method to extract the spectral and spatial features and address the aforementioned problems. To reduce the difference within the same class and obtain multilevel spatial information, morphological features (multistructuring element extended morphological profile or multiattribute filter extended multi-attribute profiles) are first obtained from the original HSI. After that, simple linear iterative clustering segmentation method is performed on each morphological feature to acquire the MMSPs. Then, uniformity constraint is used to merge the MMSPs belonging to the same class which can avoid introducing the information from different classes and acquire spatial structures at object level. Subsequently, mean filtering is utilized to extract the spatial features within and among MMSPs. At last, base kernels are obtained from the spatial features and original HSI, and several multiple kernel learning methods are used to obtain the optimal kernel to incorporate into the support vector machine. Experiments conducted on three widely used real HSIs and compared with several well-known methods demonstrate the effectiveness of the proposed model.

2. Weighted Spectral-Spatial Classification of Hyperspectral Images via Class-Specific Band Contribution

Hyperspectral images (HSIs) have evident advantages in image understanding due to enormous spectral bands, and rich spatial information. Hundreds of spectral bands, however, actually play different roles in contributing to the class-specific classification. Then, treating each band equally may lead to the underuse or overuse of them. To address this issue, this paper introduces class-specific band contributions (BCs) into the spectral space, and proposes a weighted spectral-spatial classification method for HSIs. In the method, by incorporating BC characterized by F-measure into the distance-based posterior probability, a weighted spectral posterior probability (WSP) model is established. Furthermore, to exploit the spatial information, WSP is then combined with the spatial consistency constraint via an adaptive tradeoff parameter. Additionally, aimed at obtaining the class-dependent F-measures of each band, a semisupervised F-measure prediction method is also developed. Experiments on four hyperspectral data sets are conducted. Experimental results show the superiority of our proposed method over several state-of-the-art methods in terms of three widely used indexes.

3. Discriminative Feature Learning for Unsupervised Change Detection in Heterogeneous Images Based on a Coupled Neural Network

With the application requirement, the technique for change detection based on heterogeneous remote sensing images is paid more attention. However, detecting changes between two heterogeneous images is challenging as they cannot be compared in low-dimensional space. In this paper, we construct an approximately symmetric deep neural network with two sides containing the same number of coupled layers to transform the two images into the same feature space. The two images are connected with the two sides and transformed into the same feature space, in which their features are more discriminative and the difference image can be generated by comparing paired features pixel by pixel. The network is first built by stacked restricted Boltzmann machines, and then, the parameters are updated in a special way based on clustering. The special way, motivated by that two heterogeneous images share the same reality in unchanged areas and retain respective properties in changed areas, shrinks the distance between paired features transformed from unchanged positions, and enlarges the distance between paired features extracted from changed positions. It is achieved through introducing two types of labels and updating parameters by adaptively changed learning rate. This is different from the existing methods based on deep learning that just do operations on positions predicted to be unchanged and extract only one type of labels. The whole process is completely unsupervised without any priori knowledge. Besides, the method can also be applied to homogeneous images. We test our method on heterogeneous images and homogeneous images. The proposed method achieves quite high accuracy.

4. Complex-Valued Convolutional Neural Network and Its Application in PoSAR Image Classification 这篇论文在GITHUB上有源代码可以下载

Following the great success of deep convolutional neural networks (CNNs) in computer vision, this paper proposes a complex-valued CNN (CV-CNN) specifically for synthetic aperture radar (SAR) image interpretation. It utilizes both amplitude and phase information of complex SAR imagery. All elements of CNN including input-output layer, convolution layer, activation function, and pooling layer are extended to the complex domain. Moreover, a complex backpropagation algorithm based on stochastic gradient descent is derived for CV-CNN training. The proposed CV-CNN is then tested on the typical polarimetric SAR image classification task which classifies each pixel into known terrain types via supervised training. Experiments with the benchmark data sets of Flevoland and Oberpfaffenhofen show that the classification error can be further reduced if employing CV-CNN instead of conventional real-valued CNN with the same degrees of freedom. The performance of CV-CNN is comparable to that of existing state-of-the-art methods in terms of overall classification accuracy.

5. PCA-Based Edge-Preserving Features for Hyperspectral Image Classification

Edge-preserving features (EPFs) obtained by the application of edge-preserving filters to hyperspectral images (HSIs) have been found very effective in characterizing significant spectral and spatial structures of objects in a scene. However, a direct use of the EPFs can be insufficient to provide a complete characterization of spatial information when objects of different scales are present in the considered images. Furthermore, the edge-preserving smoothing operation unavoidably decreases the spectral differences among objects of different classes, which may affect the following classification. To overcome these problems, in this paper, a novel principal component analysis (PCA)-based EPFs (PCA-EPFs) method for HSI classification is proposed, which consists of the following steps. First, the standard EPFs are constructed by applying edge-preserving filters with different parameter settings to the considered image, and the resulting EPFs are stacked together. Next, the spectral dimension of the stacked EPFs is reduced with the PCA, which not only can represent the EPFs in the mean square sense but also highlight the separability of pixels in the EPFs. Finally, the resulting PCA-EPFs are classified by a support vector machine (SVM) classifier. Experiments performed on several real hyperspectral data sets show the effectiveness of the proposed PCA-EPFs, which sharply improves the accuracy of the SVM classifier with respect to the standard edge-preserving filtering-based feature extraction method, and other widely used spectral-spatial classifiers.

11月第二周任务

王晓: 继续分析LSTM,如果效果不好可能是 GROUND TRUTH 需要重新标记

高云浩: 协同表示,进行海冰数据的实验;重新整理论文,尽量往研究对象上靠

王群: SPBL,整理代码;

王栋: 标记的数据汇总,三个ground truth reshape,汇总,有问题再提

李艳东:self-paced learning,不带BOOSTING的方法

假期任务(不断更新)

预祝各位国庆假期快乐,回家的小盆友路上注意安全,我也给大家布置了一些阅读任务,具体如下:

1. 自步学习

王栋 & 李艳东,仔细阅读 具有自学习(Self-paced learning)的集成学习(Boosting)分类器
Self-Paced Boost Learning for Classification (IJCAI 2016)
论文地址
MATLAB代码地址

此论文被IJCAI2016收录,工作的核心思想是将Boosting算法和Self-paced learning算法结合在一起,它们能够分别解决监督学习中的有效性和鲁棒性的问题。通过带self-paced样本选择法的max-margin boosting最优化,能够对数据分类的同时,保证良好的采样方式。知乎链接

2. Spatial-aware collaborative representation

王群,仔细阅读 Spatial-Aware Collaborative Representation for Hyperspectral Remote Sensing Image Classification
论文地址
MATLAB代码地址

3. three-dimensional discrete wavelet transform

高云浩,仔细阅读 Integration of 3-dimensional discrete wavelet transform and Markov random field for hyperspectral image classification
曹相湧的GoogleSite
论文地址
MATLAB代码地址

自步学习资料

现有机器学习方法都需要解决非凸优化问题,例如学习感知机或深度置信网,传统的优化方法在避免非凸优化问题陷入较差局部解时,往往采用多次随机初始化方式训练模型,然后选择其中效果最好的初始化结果构建模型。然而这种方法过于adhoc,而且计算代价过高。课程学习和自步学习最开始就是作为解决非凸优化问题而提出的。Bengio教授在2009年ICML上提出课程学习,而自步学习则是在课程学习的基础上,由Koller教授团队在2010年NIPS上将该思想建立为具有理论基础的数学表达形式。课程学习和自步学习的核心思想是通过模拟人的认知机理,首先学习简单的、普适性的知识结构,然后逐渐增加难度,过渡到学习更复杂、更专业化的知识

Han Longfei 的博客里有两篇非常好的文章,推荐阅读:

  1. 机器学习-自步学习 文章链接
  2. 机器学习-自步学习之SPLD 文章链接