Active Learning: Any Value for Classification of Remotely Sensed Data?

Abstract

Active learning, which has a strong impact on processing data prior to the classification phase, is an active research area within the machine learning community, and is now being extended for remote sensing applications. To be effective, classification must rely on the most informative pixels, while the training set should be as compact as possible. Active learning heuristics provide capability to select unlabeled data that are the "most informative" and to obtain the respective labels, contributing to both goals. Characteristics of remotely sensed image data provide both challenges and opportunities to exploit the potential advantages of active learning. We provide an overview of active learning methods, then review the latest techniques proposed to cope with the problem of interactive sampling of training pixels for classification of remotely sensed data with support vector machines. We discuss remote sensing specific approaches dealing with multi-source and spatially and time-varying data, and provide examples for high dimensional hyperspectral and very high resolution multispectral imagery.

A survey of machine learning for big data processing

“…In this way, the active learner aims to achieve high accuracy using as few labeled instances as possible, thereby minimizing the cost of obtaining labeled data [59]. It can obtain satisfactory classification performance with fewer labeled samples via query strategies than those of conventional passive learning [60]. There are three main active learning scenarios, comprising membership query synthesis, stream-based selective sampling and pool-based sampling [59].…”

Region of Interest Detection Based on Histogram Segmentation for Satellite Image

“…Supervised classification techniques which rely on labelled reference samples have been applied to classify the satellite image (Bruzzone and Persello 2009). In addition active learning, neural networks and support vector machines have all successfully been used to classify imagery (Tuia, Volpi et al 2011;Xiuming and Jing 2011;Crawford, Tuia et al 2013).…”

Concept for a Compound Analysis in Active Learning for Remote Sensing

“…Many different classifiers are currently used in the literature for active learning on remotely sensed data (Tuia et al, 2011), (Crawford et al, 2013), (Persello and Bruzzone, 2014). Today the choice of the classifier has more influence on the performance than the choice of the AL strategy (Guyon et al, 2011).…”

“…(Crawford et al, 2013) describe three ways: 1) minimize "travel distance", 2) minimize collocation, 3) incorporate segmentation problem. These methods could be incorporated by adding a fourth sub function into the compound function h.…”