Abstract
Land-cover classification is an important topic for remotely sensed hyperspectral (HS) data exploitation. In this regard, HS classifiers have to face important challenges, such as the high spectral redundancy, as well as noise, present in the data, and the fact that obtaining accurate labeled training data for supervised classification is expensive and time-consuming. As a result, the availability of large amounts of training samples, needed to alleviate the so-called Hughes phenomenon, is often unfeasible in practice. The class-imbalance problem, which results from the uneven distribution of labeled samples per class, is also a very challenging factor for HS classifiers. In this paper, a comprehensive review of oversampling techniques is provided, which mitigate the aforementioned issues by generating new samples for the minority classes. More specifically, this paper pursues a two-fold objective. Firstly, it reviews the most relevant oversampling methods that can be adopted according to the nature of HS data. Secondly, it provides a comprehensive experimental study and comparison, which are useful to derive practical conclusions about the performance of oversampling techniques in different HS image-based applications. The source will be made available publicly at https://github.com/mhaut/imbalance-review .
Funding Information
  • Consejería de Economía, Ciencia y Agenda Digital of the Junta de Extremadura
  • European Regional Development Fund of the European Union (GR21040, GR21099)
  • Spanish Ministerio de Ciencia e Innovación (PID2019-110315RB-I00)

This publication has 55 references indexed in Scilit: