Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

/pdf/convex-analysisnoer-san-nojin-zhan-nituite-5dl2rbmoyr.pdf

Convex Analysisの二,三の進展について

On robust estimation of the location parameter

A random forest (RF) classifier is an ensemble classifier that produces multiple decision trees, using a randomly selected subset of training samples and variables. This classifier has become popular within the remote sensing community due to the accuracy of its classifications. The overall objective of this work was to review the utilization of RF classifier in remote sensing. This review has revealed that RF classifier can successfully handle high data dimensionality and multicolinearity, being both fast and insensitive to overfitting. It is, however, sensitive to the sampling design. The variable importance (VI) measurement provided by the RF classifier has been extensively exploited in different scenarios, for example to reduce the number of dimensions of hyperspectral data, to identify the most relevant multisource remote sensing and geographic data, and to select the most suitable season to classify particular target classes. Further investigations are required into less commonly exploited uses of this classifier, such as for sample proximity analysis to detect and remove outliers in the training samples.

Random forest in remote sensing: A review of applications and future directions

Tensor representation is a feasible solution for analyzing large-volume, multirelational, and multimodal datasets, which are often conveniently represented as multiway arrays or tensors. It is therefore valuable and promising for the geoscience and remote sensing research communities to review tensor representation as an emerging tool for remote sensing data analysis. This chapter presents some relevant remote sensing data analysis methodologies and techniques, organized in two main topics: data fusion and feature extraction. To start with, we provide brief reviews on the mechanisms and conventional methods of both topics. We then introduce several methods that have achieved state-of-the-art performances by incorporating tensor representation into the models. Furthermore, three tensor representation-based methods are discussed in detail to demonstrate the superiority of tensor representation in remote sensing image processing. 

Tensor representation for remote sensing images

Deep convolutional networks are powerful for local feature learning and have shown advantages in image matching and registration. However, the significant differences between cross-modal images increase the challenge of image registration. The deep network should extract modality-invariant features to identify the matching samples and discriminative features to separate the nonmatching samples. The deep network can extract features invariant to the image modality changes by multiple nonlinear mapping layers. However, it does not inevitably lose rich details and affect the discrimination of features, degrading registration performances. This article proposes a novel deep wavelet learning network (DW-Net) for local feature learning. It incorporates spectral information into deep convolutional features for improving cross-modal image matching and registration. Specifically, this article aims to learn the multiresolution wavelet features through multilevel wavelet transform (WT) and the convolutional network. The cross-modal images are divided into low-frequency and high-frequency parts through WT. DW-Net can adaptively extract the shared features from the low-frequency part and useful details from the high-frequency part, which can enhance the modality invariance and discrimination of features. Additionally, the multiresolution wavelet features contain multiscale information and contribute to improving the matching accuracy. Extensive experiments demonstrate the significant advantages in terms of the accuracy and robustness of DW-Net on cross-modal remote sensing image registration. DW-Net can increase the image patch matching accuracy by 3.7% and improve image registration probability by 12.1%. Moreover, DW-Net shows strong generalization performances from low resolution to high resolution and from optical– synthetic aperture radar to other cross-modal image registration.

https://doi.org/10.1109/jstars.2023.3276409

Efficient and Robust: A Cross-Modal Registration Deep Wavelet Learning Method for Remote Sensing Images

Feature extraction ofhyperspectral remote sensing data isinvestigated. Principal component analysis (PCA)hasshown tobeagoodunsupervised feature extraction. Ontheother hand, this methods onlyfocus onsecond orders statistics. By mapping thedataontoanother feature space andusing nonlinear function, Kernel PCA(KPCA)canextract higher order statistics. Usingkernel methods, allcomputation aredonein theoriginal space, thussaving computing time.Inthis paper,KPCAisusedhasapreprocessing steptoextract relevantfeature forclassification andtoprevent fromtheHughes phenomenon. Thentheclassification wasdonewithabackpropagation neural network onreal hyperspectral ROSISdata fromurban area. Results werepositively compared tothelinearversion (PCA)andtoaversion ofaalgorithm specially designed tobeusewithneural network (DBFE).

http://ieeexplore.ieee.org/iel5/4052198/4052199/04052227.pdf

Kernel principalcomponent analysisfor feature reduction in hyperspectrale imagesanalysis

Object detection is a challenging task in remote sensing because objects only occupy a few pixels in the images, and the models are required to simultaneously learn object locations and detection. Even though the established approaches well perform for the objects of regular sizes, they achieve weak performance when analyzing small ones or getting stuck in the local minima (e.g. false object parts). Two possible issues stand in their way. First, the existing methods struggle to perform stably on the detection of small objects because of the complicated background. Second, most of the standard methods used hand-crafted features, and do not work well on the detection of objects parts of which are missing. We here address the above issues and propose a new architecture with a multiple patch feature pyramid network (MPFP-Net). Different from the current models that during training only pursue the most discriminative patches, in MPFPNet the patches are divided into class-affiliated subsets, in which the patches are related and based on the primary loss function, a sequence of smooth loss functions are determined for the subsets to improve the model for collecting small object parts. To enhance the feature representation for patch selection, we introduce an effective method to regularize the residual values and make the fusion transition layers strictly norm-preserving. The network contains bottom-up and crosswise connections to fuse the features of different scales to achieve better accuracy, compared to several state-of-the-art object detection models. Also, the developed architecture is more efficient than the baselines.

Multi-patch Feature Pyramid Network for Weakly Supervised Object Detection in Optical Remote Sensing Images

Over the last few years, there has been substantial progress in object detection on remote sensing images (RSIs) where objects are generally distributed with large-scale variations and have different types of orientations. Nevertheless, most of the current convolution neural network approaches lack the ability to deal with the challenges such as size and rotation variations. To address these problems, we propose the rotation equivariant feature image pyramid network (REFIPN), an image pyramid network based on rotation equivariance convolution. The proposed pyramid network extracts features in a wide range of scales and orientations by using novel convolution filters. These features are used to generate vector fields and determine the weight and angle of the highest-scoring orientation for all spatial locations on an image. Finally, the extracted features go through the prediction layers of the detector. The detection performance of the proposed model is validated on two commonly used aerial benchmarks and the results show our propose model can achieve state-of-the-art performance with satisfactory efficiency.

Jocelyn Chanussot

Papers

Tensor representation for remote sensing images

Efficient and Robust: A Cross-Modal Registration Deep Wavelet Learning Method for Remote Sensing Images

Kernel principalcomponent analysisfor feature reduction in hyperspectrale imagesanalysis

Multi-patch Feature Pyramid Network for Weakly Supervised Object Detection in Optical Remote Sensing Images

Rotation Equivariant Feature Image Pyramid Network for Object Detection in Optical Remote Sensing Imagery