A Semisupervised Siamese Network for Hyperspectral Image Classification

Jia, Sen; Jiang, Shuguo; Lin, Zhijie; Xu, Meng; Sun, Weiwei; Huang, Qiang; Zhu, Jiasong; Jia, Xiuping

doi:10.1109/tgrs.2021.3116138

Cited by 49 publications

(9 citation statements)

References 73 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The simplicity of the Siamese network makes it an appealing choice for addressing complex classification tasks while maintaining efficiency and ease of implementation. Furthermore, its demonstrated success in diverse applications [33][34][35] offers a strong foundation for adapting it to the specific requirements of pavement texture classification, ultimately contributing to the creation of more accurate and robust models.…”

Section: Methodsmentioning

confidence: 99%

Automatic pavement texture recognition using lightweight few-shot learning

Shuo

Yan

Liu

et al. 2023

Phil. Trans. R. Soc. A.

View full text Add to dashboard Cite

Texture is a crucial characteristic of roads, closely related to their performance. The recognition of pavement texture is of great significance for road maintenance professionals to detect potential safety hazards and carry out necessary countermeasures. Although deep learning models have been applied for recognition, the scarcity of data has always been a limitation. To address this issue, this paper proposes a few-shot learning model based on the Siamese network for pavement texture recognition with a limited dataset. The model achieved 89.8% accuracy in a four-way five-shot task classifying the pavement textures of dense asphalt concrete, micro surface, open-graded friction course and stone matrix asphalt. To align with engineering practice, global average pooling (GAP) and one-dimensional convolution are implemented, creating lightweight models that save storage and training time. Comparative experiments show that the lightweight model with GAP implemented on dense layers and one-dimensional convolution on convolutional layers reduced storage volume by 94% and training time by 99%, despite a 2.9% decrease in classification accuracy. Moreover, the model with only GAP implemented on dense layers achieved the highest accuracy at 93.5%, while reducing storage volume and training time by 83% and 6%, respectively. This article is part of the theme issue 'Artificial intelligence in failure analysis of transportation infrastructure and materials'.

show abstract

Section: Methodsmentioning

confidence: 99%

Automatic pavement texture recognition using lightweight few-shot learning

Shuo

Yan

Liu

et al. 2023

Phil. Trans. R. Soc. A.

View full text Add to dashboard Cite

show abstract

“…Eventually, the HSI pixel values X i p ∈ R p 2 ×B are mapped from an HSI patch embedding y i ∈ R d by a implicite neural representation unit, as shown in Eq. (17).…”

Section: B Generator Designmentioning

confidence: 99%

“…For example, a novel recurrent network (RNN) that can efficiently analyze HSI pixels as sequence data was first proposed by Mou et al [16] and has yielded competitive results. In [17], a semi-supervised Siamese network integrating an autoencoder and a Siamese network was proposed. This network was trained simultaneously on massive unannotated samples and few annotated samples to obtain unsupervised feature with refinement representation and unsupervised features rectified by limited labeled samples, respectively.…”

mentioning

confidence: 99%

HyperViTGAN: Semisupervised Generative Adversarial Network With Transformer for Hyperspectral Image Classification

Xia

Ghamisi

et al. 2022

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

View full text Add to dashboard Cite

“…To obtain discriminative spectral features, a siamese spectral attention network with channel consistency was proposed for few-shot HSI classification [31]. To overcome the difficult brought by limited labeled samples, the work [32] embedded an autoencoder module into siamese network with semisupervised paradigm. To upgrade the performance of siamese network under few training samples, [33] ameliorated the contrast loss function and designed a lightweight spectralspatial siamese network.…”

Section: Introductionmentioning

confidence: 99%

Bag-of-Features-Driven Spectral-Spatial Siamese Neural Network for Hyperspectral Image Classification

Xue

Zhu

Zhou³

et al. 2023

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

View full text Add to dashboard Cite

Deep learning (DL) exhibits commendable performance in HSI classification because of its powerful feature expression ability. Siamese neural network further improves the performance of DL models by learning similarities withinclass and differences between-class from sample pairs. However, there are still some limitations in siamese neural network. On the one hand, siamese neural network usually needs large number of negative pair samples in training process, leading to computing overhead. On the other hand, current models may lack interpretability because of complex network structure. To overcome the above limitations, we propose a spectral-spatial siamese neural network with Bag-of-Features (S3BoF) for HSI classification. Firstly, we use a siamese neural network with 3D and 2D convolutions to extract the spectral-spatial features. Secondly, we introduce stop-gradient operation and prediction head structure to make the siamese neural network work without negative pair samples, thus reducing computational burden. Thirdly, a Bag-of-Features (BoF) learning module is introduced to enhance the model interpretability and feature representation. Finally, a symmetric loss and a cross entropy loss are respectively used for contrastive learning and classification. Experiments results on four common hyperspectral data sets indicated that S3BoF performs better than the other traditional and stateof-the-art deep learning HSI classification methods in terms of classification accuracy and generalization performance, with improvements in terms of OA around 1.40%-30.01%, 0.27%-

show abstract

A Semisupervised Siamese Network for Hyperspectral Image Classification

Cited by 49 publications

References 73 publications

Automatic pavement texture recognition using lightweight few-shot learning

Automatic pavement texture recognition using lightweight few-shot learning

HyperViTGAN: Semisupervised Generative Adversarial Network With Transformer for Hyperspectral Image Classification

Bag-of-Features-Driven Spectral-Spatial Siamese Neural Network for Hyperspectral Image Classification

Contact Info

Product

Resources

About