Cross-Domain Few-Shot Hyperspectral Image Classification With Class-Wise Attention

Wang, Wenzhen; Liu, Fang; Liu, Jia; Xiao, Liang

doi:10.1109/tgrs.2023.3239411

Cited by 22 publications

(6 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wang et al proposed a cross-domain few-shot HSI classification method with a weak parameter-sharing mechanism to narrow the distance between two domains and used local spatial-spectral alignment to reduce classification errors [14]. For cross-domain few-shot HSI classification, Wang et al proposed a class-wise metric module and an asymmetric domain adversarial module, and the feature extractor can pay more attention to discriminative local information between classes [15]. Huang et al proposed a cross-domain learning strategy for few-shot HSI classification by using kernel triplet loss to characterize complex nonlinear relationships between samples [16].…”

Section: Introductionmentioning

confidence: 99%

AL-MRIS: An Active Learning-Based Multipath Residual Involution Siamese Network for Few-Shot Hyperspectral Image Classification

Yang,

Qin,

Qian

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

In hyperspectral image (HSI) classification scenarios, deep learning-based methods have achieved excellent classification performance, but often rely on large-scale training datasets to ensure accuracy. However, in practical applications, the acquisition of hyperspectral labeled samples is time consuming, labor intensive and costly, which leads to a scarcity of obtained labeled samples. Suffering from insufficient training samples, few-shot sample conditions limit model training and ultimately affect HSI classification performance. To solve the above issues, an active learning (AL)-based multipath residual involution Siamese network for few-shot HSI classification (AL-MRIS) is proposed. First, an AL-based Siamese network framework is constructed. The Siamese network, which has relatively low demand for sample data, is adopted for classification, and the AL strategy is integrated to select more representative samples to improve the model’s discriminative ability and reduce the costs of labeling samples in practice. Then, the multipath residual involution (MRIN) module is designed for the Siamese subnetwork to obtain the comprehensive features of the HSI. The involution operation was used to capture the fine-grained features and effectively aggregate the contextual semantic information of the HSI through dynamic weights. The MRIN module comprehensively considers the local features, dynamic features and global features through multipath residual connections, which improves the representation ability of HSIs. Moreover, a cosine distance-based contrastive loss is proposed for the Siamese network. By utilizing the directional similarity of high-dimensional HSI data, the discriminability of the Siamese classification network is improved. A large number of experimental results show that the proposed AL-MRIS method can achieve excellent classification performance with few-shot training samples, and compared with several state-of-the-art classification methods, the AL-MRIS method obtains the highest classification accuracy.

show abstract

Section: Introductionmentioning

confidence: 99%

AL-MRIS: An Active Learning-Based Multipath Residual Involution Siamese Network for Few-Shot Hyperspectral Image Classification

Yang,

Qin,

Qian

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The residual attention mechanism (RAM) introduced residual branches to fuse shallow features and control the spatial semantics padding of trunk branches [28]. These approaches adjust the evaluation manner of attention mechanisms and obtain more accurate attention weights to emphasize the important objects [29]. However, controllable factors lack the dynamic adjustment ability to adapt to the complex and continuous feature environment of HSI.…”

Section: Introductionmentioning

confidence: 99%

Spectral-Spatial-Sensorial Attention Network with Controllable Factors for Hyperspectral Image Classification

Li,

Wang,

Cheng

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Hyperspectral image (HSI) classification aims to recognize categories of objects based on spectral–spatial features and has been used in a wide range of real-world application areas. Attention mechanisms are widely used in HSI classification for their ability to focus on important information in images automatically. However, due to the approximate spectral–spatial features in HSI, mainstream attention mechanisms are difficult to accurately distinguish the small difference, which limits the classification accuracy. To overcome this problem, a spectral–spatial-sensorial attention network (S3AN) with controllable factors is proposed to efficiently recognize different objects. Specifically, two controllable factors, dynamic exponential pooling (DE-Pooling) and adaptive convolution (Adapt-Conv), are designed to enlarge the difference in approximate features and enhance the attention weight interaction. Then, attention mechanisms with controllable factors are utilized to build the redundancy reduction module (RRM), feature learning module (FLM), and label prediction module (LPM) to process HSI spectral–spatial features. The RRM utilizes the spectral attention mechanism to select representative band combinations, and the FLM introduces the spatial attention mechanism to highlight important objects. Furthermore, the sensorial attention mechanism extracts location and category information in a pseudo label to guide the LPM for label prediction and avoid details from being ignored. Experimental results on three public HSI datasets show that the proposed method is able to accurately recognize different objects with an overall accuracy (OA) of 98.69%, 98.89%, and 97.56%, respectively.

show abstract

“…Fully and reasonably utilizing spatial association information can improve the performance of classifiers [26]. Recently, graph convolutional neural networks (GCNs) in the deep learning field have been applied to urban land cover classification work [27,28]. Researchers applied GCN to obtain spatial association information between segments and neighboring segments [26,29].…”

Section: Introductionmentioning

confidence: 99%

An Urban Land Cover Classification Method Based on Segments’ Multidimension Feature Fusion

Huang,

Cheng,

Wei

et al. 2024

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

View full text Add to dashboard Cite

Using object-based deep learning for the urban land cover classification has become a mainstream method. This study proposed an urban land cover classification method based on segments' object features, deep features and spatial association features. The proposed method used the synthetic semivariance function to determine the hyperparameters of the superpixel segmentation and subsequently optimized the image superpixel segmentation result. A convolutional neural network (CNN) and a graph convolutional neural network (GCN) were used to obtain segments' deep features and spatial association features respectively. The random forest algorithm was used to classify segments based on the multi-dimension features. The results showed that the image superpixel segmentation results had the significant impact on the classification results. Compared with the pixel-based method, the segment-based methods generally yielded the higher classification accuracy. The strategy of multi-dimension feature fusion can combine the advantages of each singledimension feature to improve the classification accuracy. The proposed method utilizing multi-dimension features was more efficient than traditional methods used for the urban land cover classification. The fusion of segments' object features, deep features and spatial association features was the best solution for achieving the urban land cover classification.

show abstract

Cross-Domain Few-Shot Hyperspectral Image Classification With Class-Wise Attention

Cited by 22 publications

References 49 publications

AL-MRIS: An Active Learning-Based Multipath Residual Involution Siamese Network for Few-Shot Hyperspectral Image Classification

AL-MRIS: An Active Learning-Based Multipath Residual Involution Siamese Network for Few-Shot Hyperspectral Image Classification

Spectral-Spatial-Sensorial Attention Network with Controllable Factors for Hyperspectral Image Classification

An Urban Land Cover Classification Method Based on Segments’ Multidimension Feature Fusion

Contact Info

Product

Resources

About