Hyperspectral Image Classification Using Group-Aware Hierarchical Transformer

Mei, Shaohui; Song, Chao; Ma, Mingyang; Xu, Fulin

doi:10.1109/tgrs.2022.3207933

Cited by 141 publications

(28 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CNN-based networks include 1D CNN [14], 2D CNN [60], 3D CNN [61], RNN [21], SSRN [27], HybridSN [31], and RIAN [13]. Transformer-based methods contain SF [45], SSFTT [46], and GAHT [47].…”

Section: Compared Methodsmentioning

confidence: 99%

“…• 1D CNN [14]: This method uses two 1D convolutional layers to extract features. GAHT [47]: This work utilizes the hierarchical transformer network with the grouped pixel embedding module. This module confines the multi-head self-attention for extracting the spatial-spectral feature.…”

Section: Compared Methodsmentioning

confidence: 99%

“…The main reason is that the sample area is regular and dense, so as the local spatial information increases, it can provide more effective classification information. In other words, the IP and SA database has more significant smooth regions [47]. Thus, the patch size of the SA dataset is set to 15 × 15.…”

Section: Size Of Hsi Patchesmentioning

confidence: 99%

“…The vision transformer (ViT) [44] has recently performed remarkably on some visionrelated tasks. As a result, some studies [45][46][47] have attempted to apply ViT to hyperspectral classification. For instance, a novel local transformer [48] with an integrated spatial partition restore module is proposed for classification.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Spectral-Spatial Attention Rotation-Invariant Classification Network for Airborne Hyperspectral Images

Shi

Wang

et al. 2023

Drones

View full text Add to dashboard Cite

An airborne hyperspectral imaging system is typically equipped on an aircraft or unmanned aerial vehicle (UAV) to capture ground scenes from an overlooking perspective. Due to the rotation of the aircraft or UAV, the same region of land cover may be imaged from different viewing angles. While humans can accurately recognize the same objects from different viewing angles, classification methods based on spectral-spatial features for airborne hyperspectral images exhibit significant errors. The existing methods primarily involve incorporating image or feature rotation angles into the network to improve its accuracy in classifying rotated images. However, these methods introduce additional parameters that need to be manually determined, which may not be optimal for all applications. This paper presents a spectral-spatial attention rotation-invariant classification network for the airborne hyperspectral image to address this issue. The proposed method does not require the introduction of additional rotation angle parameters. There are three modules in the proposed framework: the band selection module, the local spatial feature enhancement module, and the lightweight feature enhancement module. The band selection module suppresses redundant spectral channels, while the local spatial feature enhancement module generates a multi-angle parallel feature encoding network to improve the discrimination of the center pixel. The multi-angle parallel feature encoding network also learns the position relationship between each pixel, thus maintaining rotation invariance. The lightweight feature enhancement module is the last layer of the framework, which enhances important features and suppresses insignificance features. At the same time, a dynamically weighted cross-entropy loss is utilized as the loss function. This loss function adjusts the model’s sensitivity for samples with different categories according to the output in the training epoch. The proposed method is evaluated on five airborne hyperspectral image datasets covering urban and agricultural regions. Compared with other state-of-the-art classification algorithms, the method achieves the best classification accuracy and is capable of effectively extracting rotation-invariant features for urban and rural areas.

show abstract

“…CNN-based networks include 1D CNN [14], 2D CNN [60], 3D CNN [61], RNN [21], SSRN [27], HybridSN [31], and RIAN [13]. Transformer-based methods contain SF [45], SSFTT [46], and GAHT [47].…”

Section: Compared Methodsmentioning

confidence: 99%

Section: Compared Methodsmentioning

confidence: 99%

Section: Size Of Hsi Patchesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Spectral-Spatial Attention Rotation-Invariant Classification Network for Airborne Hyperspectral Images

Shi

Wang

et al. 2023

Drones

View full text Add to dashboard Cite

show abstract

“…Zhang proposed a convolution transformer mixer (CTMixer) network combining the advantages of a vision transformer and convolutional neural network, which also use the MHSA mechanism to improve classification accuracy [59]. Mei built a multi-head selfattention that encodes the semantic context-aware representation to obtain discriminative features [60]. He proposed the HSI-BERT model, which has a generalization ability using the MHSA layer.…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral Image Classification Based on 3-D Multihead Self-Attention Spectral–Spatial Feature Fusion Network

Qigao

Zhou

Shen

et al. 2023

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

View full text Add to dashboard Cite

Convolutional neural networks are a popular method in hyperspectral image classification. However, the accuracy of the models is closely related to the number and spatial size of training samples. Which relieve the performance decline by the number and spatial size of training samples, we designed a 3D multi-head self-attention spectral-spatial feature fusion network (3DMHSA-SSFFN) that contains step-by-step feature extracted blocks (SBSFE) and 3D multi-head-self-attention-module (3DMHSA). The proposed step-by-step feature extracted blocks relieved the declining-accuracy phenomenon for the limited number of training samples. Multi-scale convolution kernels extract more spatial-spectral features in the step-by-step feature-extracted blocks. In hyperspectral image classification, the 3DMHSA module enhances the stability of classification by correlating disparate features. Experimental results show that 3DMHSA-SSFFN possesses a better classification performance than other advanced models through the limited number of balance and imbalance training data in three data.

show abstract