paper-with-me

홈 › Papers

3D-Convolution Guided Spectral-Spatial Transformer for Hyperspectral Image Classification

2024-04-20 · Shyam Varahagiri, Aryaman Sinha, Shiv Ram Dubey, Satish Kumar Singh

In recent years, Vision Transformers (ViTs) have shown promising classification performance over Convolutional Neural Networks (CNNs) due to their self-attention mechanism. Many researchers have incorporated ViTs for Hyperspectral Image (HSI) classification. HSIs are characterised by narrow contiguous spectral bands, providing rich spectral data. Although ViTs excel with sequential data, they cannot extract spectral-spatial information like CNNs. Furthermore, to have high classification performance, there should be a strong interaction between the HSI token and the class (CLS) token. To solve these issues, we propose a 3D-Convolution guided Spectral-Spatial Transformer (3D-ConvSST) for HSI classification that utilizes a 3D-Convolution Guided Residual Module (CGRM) in-between encoders to "fuse" the local spatial and spectral information and to enhance the feature propagation. Furthermore, we forego the class token and instead apply Global Average Pooling, which effectively encodes more discriminative and pertinent high-level features for classification. Extensive experiments have been conducted on three public HSI datasets to show the superiority of the proposed model over state-of-the-art traditional, convolutional, and Transformer models. The code is available at https://github.com/ShyamVarahagiri/3D-ConvSST.

📄 PDF Abstract BibTeX arXiv:2404.13252

Code (1)

shyamvarahagiri/3d-convsst 공식 구현 pytorch

Tasks

ClassificationHyperspectral Image Classificationimage-classificationImage Classification

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

MultiScale Spectral-Spatial Convolutional Transformer for Hyperspectral Image Classification

2023-10-28 · Zhiqiang Gong, Xian Zhou, Wen Yao

Due to the powerful ability in capturing the global information, Transformer has become an alternative architecture of CNNs for hyperspectral image classification. However, general Transformer mainly considers the global…

ClassificationHyperspectral Image Classificationimage-classificationImage Classification

Efficient Hyperspectral Image Reconstruction Using Lightweight Separate Spectral Transformers

2026-01-03 · Jianan Li, Wangcai Zhao, Tingfa Xu arxiv

Hyperspectral imaging (HSI) is essential across various disciplines for its capacity to capture rich spectral information. However, efficiently reconstructing hyperspectral images from compressive sensing measurements pr…

Image ReconstructionCompressive Sensing

Fusformer: A Transformer-based Fusion Approach for Hyperspectral Image Super-resolution

2021-09-05 · Jin-Fan Hu, Ting-Zhu Huang, Liang-Jian Deng

Hyperspectral image has become increasingly crucial due to its abundant spectral information. However, It has poor spatial resolution with the limitation of the current imaging mechanism. Nowadays, many convolutional neu…

Hyperspectral Image Super-ResolutionImage Super-ResolutionSuper-Resolution

Spectral-Enhanced Transformers: Leveraging Large-Scale Pretrained Models for Hyperspectral Object Tracking

2025-02-26 · Shaheer Mohamed, Tharindu Fernando, Sridha Sridharan, Peyman Moghadam 외

Hyperspectral object tracking using snapshot mosaic cameras is emerging as it provides enhanced spectral information alongside spatial data, contributing to a more comprehensive understanding of material properties. Usin…

ObjectObject Tracking

Cross-Scope Spatial-Spectral Information Aggregation for Hyperspectral Image Super-Resolution

2023-11-29 · Shi Chen, Lefei Zhang, Liangpei Zhang

Hyperspectral image super-resolution has attained widespread prominence to enhance the spatial resolution of hyperspectral images. However, convolution-based methods have encountered challenges in harnessing the global s…

Hyperspectral Image Super-ResolutionImage Super-ResolutionSuper-Resolution