# Efficient Dynamic Attention 3D Convolution for Hyperspectral Image Classification

arXiv: https://arxiv.org/abs/2503.23472 · HTML: https://mlsanity.com/paper/2503.23472/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 31 references that are in the map.
- First posted on arXiv 30 Mar 2025.

## Builds on (most cited first, 14 of 14)

- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://mlsanity.com/paper/1807.11626/) (2018)
- [Learning Efficient Convolutional Networks through Network Slimming](https://mlsanity.com/paper/1708.06519/) (2017)
- [SkipNet: Learning Dynamic Routing in Convolutional Networks](https://mlsanity.com/paper/1711.09485/) (2017)
- [SpectralFormer: Rethinking Hyperspectral Image Classification with Transformers](https://mlsanity.com/paper/2107.02988/) (2021)
- [Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions](https://mlsanity.com/paper/1711.08141/) (2017)
- [Going Deeper with Contextual CNN for Hyperspectral Image Classification](https://mlsanity.com/paper/1604.03519/) (2016)
- [Faster hyperspectral image classification based on selective kernel mechanism using deep convolutional networks](https://mlsanity.com/paper/2202.06458/) (2022)
- [DGCNet: An Efficient 3D-Densenet based on Dynamic Group Convolution for Hyperspectral Remote Sensing Image Classification](https://mlsanity.com/paper/2307.06667/) (2023)
- [Spatial-Spectral Hyperspectral Classification based on Learnable 3D Group Convolution](https://mlsanity.com/paper/2307.07720/) (2023)
- [Dual Classification Head Self-training Network for Cross-scene Hyperspectral Image Classification](https://mlsanity.com/paper/2502.17879/) (2025)

## Built on by (most cited first, 6 of 6)

- [Spatial-Geometry Enhanced 3D Dynamic Snake Convolutional Neural Network for Hyperspectral Image Classification](https://mlsanity.com/paper/2504.04463/) (2025)
- [3D Wavelet Convolutions with Extended Receptive Fields for Hyperspectral Image Classification](https://mlsanity.com/paper/2504.10795/) (2025)
- [Expert Kernel Generation Network Driven by Contextual Mapping for Hyperspectral Image Classification](https://mlsanity.com/paper/2504.13045/) (2025)
- [Dynamic 3D KAN Convolution with Adaptive Grid Optimization for Hyperspectral Image Classification](https://mlsanity.com/paper/2504.15155/) (2025)
- [Hyperspectral Image Classification via Transformer-based Spectral-Spatial Attention Decoupling and Adaptive Gating](https://mlsanity.com/paper/2506.08324/) (2025)
- [MVNet: Hyperspectral Remote Sensing Image Classification Based on Hybrid Mamba-Transformer Vision Backbone Architecture](https://mlsanity.com/paper/2507.04409/) (2025)

## Abstract (arXiv)

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.