Papers › HSI-BERT: Hyperspectral Image Classification Using the Bidirectional Encoder...

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

4 Sep 2019IEEE Transactions on Geoscience and Remote Sensing 2019 9archive 2025-07-28

Ji He, Lina Zhao, HongWei Yang, Mengmeng Zhang, Wei Li

Deep learning methods have been widely used in hyperspectral image classification and have achieved state-of-the-art performance. Nonetheless, the existing deep learning methods are restricted by a limited receptive field, inflexibility, and difficult generalization problems in hyperspectral image classification. To solve these problems, we propose HSI-BERT, where BERT stands for bidirectional encoder representations from transformers and HSI stands for hyperspectral imagery. The proposed HSI-BERT has a global receptive field that captures the global dependence among pixels regardless of their spatial distance. HSI-BERT is very flexible and enables the flexible and dynamic input regions. Furthermore, HSI-BERT has good generalization ability because the jointly trained HSI-BERT can be generalized from regions with different shapes without retraining. HSI-BERT is primarily built on a multihead self-attention (MHSA) mechanism in an MHSA layer. Moreover, several attentions are learned by different heads, and each head of the MHSA layer encodes the semantic context-aware representation to obtain discriminative features. Because all head-encoded features are merged, the resulting features exhibit spatial-spectral information that is essential for accurate pixel-level classification. Quantitative and qualitative results demonstrate that HSI-BERT outperforms any other CNN-based model in terms of both classification accuracy and computational time and achieves state-of-the-art performance on three widely used hyperspectral image data sets.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ClassificationFew-Shot Image ClassificationHyperspectral Image ClassificationImage Classificationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Hyperspectral Image Classification Indian Pines HSI-BERT OA@15perclass 58.50±1.56 #12 of 34 Archive leaderboard report
Hyperspectral Image Classification Kennedy Space Center HSI-BERT OA@15perclass 82.93±0.94 #9 of 14 Archive leaderboard report
Hyperspectral Image Classification Pavia University HSI-BERT OA@15perclass 75.31±1.59 #11 of 33 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections