An Unsupervised Band Selection Method via Contrastive Learning for Hyperspectral Images
Open Access
- 25 November 2023
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 15 (23) , 5495
Abstract
Band selection (BS) is an efficacious approach to reduce hyperspectral information redundancy while preserving the physical meaning of hyperspectral images (HSIs). Recently, deep learning-based BS methods have received widespread interest due to their ability to model the nonlinear relationship between bands, with existing methods typically relying on generative algorithms. However, the process of generating images with pixel-level detail required by generative algorithm-based BS methods is computationally expensive. To alleviate this issue, we propose a contrastive learning-based unsupervised BS architecture, termed ContrastBS, in this article. With the help of contrastive learning, the proposed architecture avoids the costly generation step in pixel space by learning to distinguish data at the abstract semantic level of the feature space. Specifically, ContrastBS combines an attention mechanism with contrastive learning to extract the importance of each band. Furthermore, we design a novel loss function, which is able to constrain the symmetric loss while ensuring attention to the most valuable bands, for the contrastive learning-based BS network. Experimental results indicate that ContrastBS has excellent classification performance and competitive time cost compared to the comparison methods.Keywords
Funding Information
- Joint Fund Project of the Chinese Ministry of Education (8091B022118, 62171404)
- National Natural Science Foundation of China (8091B022118, 62171404)
This publication has 36 references indexed in Scilit:
- Discovering the Representative Subset with Low Redundancy for Hyperspectral Feature SelectionRemote Sensing, 2019
- A Fast Hyperspectral Feature Selection Method Based on Band Correlation AnalysisIEEE Geoscience and Remote Sensing Letters, 2018
- Unsupervised Feature Learning via Non-parametric Instance Discrimination2018
- A Geometry-Based Band Selection Approach for Hyperspectral Image AnalysisIEEE Transactions on Geoscience and Remote Sensing, 2018
- Salient Band Selection for Hyperspectral Image Classification via Manifold RankingIEEE Transactions on Neural Networks and Learning Systems, 2016
- Exemplar Component Analysis: A Fast Band Selection Method for Hyperspectral ImageryIEEE Geoscience and Remote Sensing Letters, 2014
- Segmentation and classification of hyperspectral images using watershed transformationPattern Recognition, 2010
- Dimensionality Reduction by Learning an Invariant Mapping2006
- Constrained band selection for hyperspectral imageryIEEE Transactions on Geoscience and Remote Sensing, 2006
- A joint band prioritization and band-decorrelation approach to band selection for hyperspectral image classificationIEEE Transactions on Geoscience and Remote Sensing, 1999