paper-with-me

Papers

Efficient Dynamic Attention 3D Convolution for Hyperspectral Image Classification

2025-03-30 · Guandong Li, Mengxia Ye

Deep neural networks face several challenges in hyperspectral image classification, including insufficient utilization of joint spatial-spectral information, gradient vanishing with increasing depth, and overfitting. To enhance feature extraction efficiency while skipping redundant information, this paper proposes a dynamic attention convolution design based on an improved 3D-DenseNet model. The design employs multiple parallel convolutional kernels instead of a single kernel and assigns dynamic attention weights to these parallel convolutions. This dynamic attention mechanism achieves adaptive feature response based on spatial characteristics in the spatial dimension of hyperspectral images, focusing more on key spatial structures. In the spectral dimension, it enables dynamic discrimination of different bands, alleviating information redundancy and computational complexity caused by high spectral dimensionality. The DAC module enhances model representation capability by attention-based aggregation of multiple convolutional kernels without increasing network depth or width. The proposed method demonstrates superior performance in both inference speed and accuracy, outperforming mainstream hyperspectral image classification methods on the IN, UP, and KSC datasets.

📄 PDF Abstract BibTeX arXiv:2503.23472

Code (1)

leeguandong/DACNet-for-HSI 공식 구현 pytorch

Tasks

Hyperspectral Image Classificationimage-classificationImage Classification

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…
DAC 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Multi-scale Dynamic Graph Convolutional Network for Hyperspectral Image Classification

2019-05-14 · Sheng Wan, Chen Gong, Ping Zhong, Bo Du 외

Convolutional Neural Network (CNN) has demonstrated impressive ability to represent hyperspectral images and to achieve promising results in hyperspectral image classification. However, traditional CNN models can only op…

ClassificationGeneral ClassificationHyperspectral Image Classificationimage-classification+1

Hyperspectral Image Classification with Attention Aided CNNs

2020-05-25 · Renlong Hang, Zhu Li, Qingshan Liu, Pedram Ghamisi 외

Convolutional neural networks (CNNs) have been widely used for hyperspectral image classification. As a common process, small cubes are firstly cropped from the hyperspectral image and then fed into CNNs to extract spect…

ClassificationGeneral ClassificationHyperspectral Image Classificationimage-classification+1

Expert Kernel Generation Network Driven by Contextual Mapping for Hyperspectral Image Classification

2025-04-17 · Guandong Li, Mengxia Ye

Deep neural networks face several challenges in hyperspectral image classification, including high-dimensional data, sparse distribution of ground objects, and spectral redundancy, which often lead to classification over…

Hyperspectral Image Classificationimage-classificationImage Classification

CLAReSNet: When Convolution Meets Latent Attention for Hyperspectral Image Classification

2025-11-15 · Asmit Bandyopadhyay, Anindita Das Bhattacharjee, Rakesh Das arxiv

Hyperspectral image (HSI) classification faces critical challenges, including high spectral dimensionality, complex spectral-spatial correlations, and limited training samples with severe class imbalance. While CNNs exce…

Hyperspectral Image Classification

DGCNet: An Efficient 3D-Densenet based on Dynamic Group Convolution for Hyperspectral Remote Sensing Image Classification

2023-07-13 · Guandong Li

Deep neural networks face many problems in the field of hyperspectral image classification, lack of effective utilization of spatial spectral information, gradient disappearance and overfitting as the model depth increas…

Hyperspectral Image Classificationimage-classificationImage ClassificationRemote Sensing Image Classification