LESSFormer: Local-Enhanced Spectral-Spatial Transformer for Hyperspectral Image Classification

Zou, Jiaqi; Wei, He; Zhang, Hongyan

doi:10.1109/tgrs.2022.3196771

Cited by 39 publications

(4 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sun et al [16] introduce the SSFTT, which incorporates a Gaussian weighted token module into the transformer architecture to extract highlevel semantic features, leading to improved performance. Zou et al [19] design the LESSFormer, including the HSI2Token module and a local-enhanced transformer encoder. This design adaptively generates spectral-spatial tokens and concurrently enhances local information while preserving global context.…”

Section: A Deep Learning-based Methods For Hsi Classificationmentioning

confidence: 99%

Spatial Proximity Feature Selection With Residual Spatial–Spectral Attention Network for Hyperspectral Image Classification

Zhang

Wang

2023

IEEE Access

View full text Add to dashboard Cite

Over the past few years, deep learning has been introduced to tackle hyperspectral image (HSI) classification and demonstrated good performance. In particular, the convolutional neural network (CNN) based methods have progressed. However, due to the high dimensionality of HSI and equal treatment of all bands, the performances of CNN based methods are hampered. The labels of land-covers often differ between edge and the center pixels in pixel-centered spatial information. These edge pixels may weaken the discrimination of spatial features and reduce classification accuracy. Motivated by the attention mechanism of the human visual system, the spatial proximity feature selection with residual spatial-spectral attention network is proposed in this article. It contains a residual spatial attention module, a residual spectral attention module, and a spatial proximity feature selection module. The residual spatial attention module aims to select the crucial spatial information, which assigns weights to different features by measuring the similarity between the surrounding elements and their central ones. The residual spectral attention module is designed for spectral bands which are selected from raw input data by emphasizing the valuable bands and suppressing the valueless. According to the spatial distribution of features, the spatial proximity feature selection module is used to filter features effectively. Experiments on three public data sets demonstrate that the proposed network outperforms the state-of-the-art methods in comparison.

show abstract

Section: A Deep Learning-based Methods For Hsi Classificationmentioning

confidence: 99%

Spatial Proximity Feature Selection With Residual Spatial–Spectral Attention Network for Hyperspectral Image Classification

Zhang

Wang

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…For the supervised segmentation loss, we employ the conventional cross-entropy loss function [30], [31] to minimize the disparity between the segmentation results and their corresponding reference labels, i.e.,…”

Section: Loss Functionmentioning

confidence: 99%

Cross-City Semantic Segmentation (C2Seg) in Multimodal Remote Sensing: Outcome of the 2023 IEEE WHISPERS C2Seg Challenge

Liu,

Wang,

Zhang

et al. 2024

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

Self Cite

View full text Add to dashboard Cite

Given the ever-growing availability of remote sensing data (e.g., Gaofen in China, Sentinel in the EU, and Landsat in the USA), multimodal remote sensing techniques have been garnering increasing attention and have made extraordinary progress in various Earth observation (EO)-related tasks. The data acquired by different platforms can provide diverse and complementary information. The joint exploitation of multimodal remote sensing has been proven effective in improving the existing methods of land-use/land-cover segmentation in urban environments. To boost technical breakthroughs and accelerate the development of EO applications across cities and regions, one important task is to build novel cross-city semantic segmentation models based on modern artificial intelligence technologies and emerging multimodal remote sensing data. This leads to the development of better semantic segmentation models with high transferability among different cities and regions. The Cross-City Semantic Segmentation contest is organized in conjunction with the 13th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS).

show abstract

“…On the one hand, CNNs utilizing local extraction and global parameter sharing mechanisms focus more on spatial content information, potentially losing spectral diagnostic features to some extent [39]. On the other hand, transformer based on global selfattention can effectively model long-range dependencies but often overlook the spatial priors near pixels, which are often more relevant than distant pixels [40]. Therefore, the hybrid structure of CNN and transformer enables the model to capture local spatial information while describing both spatial longrange dependencies and spectral correlations, enhancing the representational capacity of features.…”

Section: Introductionmentioning

confidence: 99%

Decoupled Knowledge Distillation via Spatial Feature Blurring for Hyperspectral Image Classification

Xie,

Zhang,

Jiao

et al. 2024

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

View full text Add to dashboard Cite

LESSFormer: Local-Enhanced Spectral-Spatial Transformer for Hyperspectral Image Classification

Cited by 39 publications

References 50 publications

Spatial Proximity Feature Selection With Residual Spatial–Spectral Attention Network for Hyperspectral Image Classification

Spatial Proximity Feature Selection With Residual Spatial–Spectral Attention Network for Hyperspectral Image Classification

Cross-City Semantic Segmentation (C2Seg) in Multimodal Remote Sensing: Outcome of the 2023 IEEE WHISPERS C2Seg Challenge

Decoupled Knowledge Distillation via Spatial Feature Blurring for Hyperspectral Image Classification

Contact Info

Product

Resources

About