HSI-BERT: Hyperspectral Image Classification Using the Bidirectional Encoder Representation From Transformers

He, Ji; Zhao, Lan; Yang, Hong-Wei; Zhang, Mengmeng; Li, Wei

doi:10.1109/tgrs.2019.2934760

Cited by 276 publications

(88 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Transformer was first introduced in NLP as an efficient alternative to RNNs [28], which has been introduced to some remote sensing tasks, such as hyperspectral image classification [53], image captioning [54], and SITS classification [29].…”

Section: Transformer Encodermentioning

confidence: 99%

Self-Supervised Pretraining of Transformers for Satellite Image Time Series Classification

Yuan

Lin

2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

118

View full text Add to dashboard Cite

Section: Transformer Encodermentioning

confidence: 99%

Self-Supervised Pretraining of Transformers for Satellite Image Time Series Classification

Yuan

Lin

2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

118

View full text Add to dashboard Cite

“…Transformer was first introduced in NLP as an efficient alternative to RNNs [28], which has been introduced to some remote sensing tasks, such as hyperspectral image classification [54], image captioning [55], and SITS classification [29].…”

Section: Transformer Encodermentioning

confidence: 99%

Self-Supervised Pre-Training of Transformers for Satellite Image Time Series Classification

Yuan¹,

Liu²

2020

Preprint

View full text Add to dashboard Cite

<div>Satellite image time series (SITS) classification is a major research topic in remote sensing and is relevant for a wide range of applications. Deep learning approaches have been commonly employed for SITS classification and have provided state-of-the-art performance. However, deep learning methods suffer from overfitting when labeled data is scarce. To address this problem, we propose a novel self-supervised pre-training scheme to initialize a Transformer-based network by utilizing large-scale unlabeled data. In detail, the model is asked to predict randomly contaminated observations given an entire time series of a pixel. The main idea of our proposal is to leverage the inherent temporal structure of satellite time series to learn general-purpose spectral-temporal representations related to land cover semantics. Once pre-training is completed, the pre-trained network can be further adapted to various SITS classification tasks by fine-tuning all the model parameters on small-scale task-related labeled data. In this way, the general knowledge and representations about SITS can be transferred to a label-scarce task, thereby improving the generalization performance of the model as well as reducing the risk of overfitting. Comprehensive experiments have been carried out on three benchmark datasets over large study areas. Experimental results demonstrate the effectiveness of the proposed method, leading to a classification accuracy increment up to 2.38% to 5.27%. The code and the pre-trained model will be available at https://github.com/linlei1214/SITS-BERT upon publication.</div><div><b>This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.</b></div>

show abstract

“…Transformer was first introduced in NLP as an efficient alternative to RNNs [25], which has been introduced to some remote sensing tasks, such as hyperspectral image classification [51], image captioning [52], and SITS classification [26].…”

Section: Transformer Encodermentioning

confidence: 99%

Self-Supervised Pre-Training of Transformers for Satellite Image Time Series Classification

Yuan¹,

Liu²

2020

Preprint

View full text Add to dashboard Cite

Satellite image time series (SITS) classification is a major research topic in remote sensing and is relevant for a wide range of applications. Deep learning approaches have been commonly employed for SITS classification and have provided state-of-the-art performance. However, deep learning methods suffer from overfitting when labeled data is scarce. To address this problem, we propose a novel self-supervised pre-training scheme to initialize a Transformer-based network by utilizing large-scale unlabeled data. In detail, the model is asked to predict randomly contaminated observations given an entire time series of a pixel. The main idea of our proposal is to leverage the inherent temporal structure of satellite time series to learn general-purpose spectral-temporal representations related to land cover semantics. Once pre-training is completed, the pre-trained network can be further adapted to various SITS classification tasks by fine-tuning all the model parameters on small-scale task-related labeled data. In this way, the general knowledge and representations about SITS can be transferred to a label-scarce task, thereby improving the generalization performance of the model as well as reducing the risk of overfitting. Comprehensive experiments have been carried out on three benchmark datasets over large study areas. Experimental results demonstrate the effectiveness of the proposed method, leading to a classification accuracy increment up to 1.91% to 6.69%. <div><b>This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.</b></div>

show abstract

HSI-BERT: Hyperspectral Image Classification Using the Bidirectional Encoder Representation From Transformers

Cited by 276 publications

References 34 publications

Self-Supervised Pretraining of Transformers for Satellite Image Time Series Classification

Self-Supervised Pretraining of Transformers for Satellite Image Time Series Classification

Self-Supervised Pre-Training of Transformers for Satellite Image Time Series Classification

Self-Supervised Pre-Training of Transformers for Satellite Image Time Series Classification

Contact Info

Product

Resources

About