A Comprehensive Survey of Imbalance Correction Techniques for Hyperspectral Data Classification
Open Access
- 24 May 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 16 (19391404) , 5297-5314
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 .Keywords
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:
- Study of the impact of resampling methods for contrast pattern based classifiers in imbalanced databasesNeurocomputing, 2016
- Remote sensing big data computing: Challenges and opportunitiesFuture Generation Computer Systems, 2015
- Imbalanced Hyperspectral Image Classification Based on Maximum MarginIEEE Geoscience and Remote Sensing Letters, 2014
- Advances in Hyperspectral Image Classification: Earth Monitoring with Statistical Learning MethodsIEEE Signal Processing Magazine, 2013
- Support vector machines in remote sensing: A reviewISPRS Journal of Photogrammetry and Remote Sensing, 2011
- Borderline over-sampling for imbalanced data classificationInternational Journal of Knowledge Engineering and Soft Data Paradigms, 2011
- Borderline-SMOTE: A New Over-Sampling Method in Imbalanced Data Sets Learning2005
- EditorialACM SIGKDD Explorations Newsletter, 2004
- Detection algorithms for hyperspectral imaging applicationsIEEE Signal Processing Magazine, 2002
- Hyperspectral image data analysisIEEE Signal Processing Magazine, 2002