Adaptive pixel attention network for hyperspectral image classification
Abstract Patch features obtained by fixed convolution kernel have become the main form in hyperspectral image (HSI) classification processing. However, the fixed convolution kernel limits the weight learning of channels, which results in the potential connections between pixels not being captured in...
Saved in:
| Main Authors: | Yuefeng Zhao, Chengmin Zai, Nannan Hu, Lu Shi, Xue Zhou, Jingqi Sun |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-11-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-024-73988-3 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Residual channel attention based sample adaptation few-shot learning for hyperspectral image classification
by: Yuefeng Zhao, et al.
Published: (2024-11-01) -
Adaptive Pixel-Level and Superpixel-Level Feature Fusion Transformer for Hyperspectral Image Classification
by: Wei Huang, et al.
Published: (2024-01-01) -
Central Pixel-Based Dual-Branch Network for Hyperspectral Image Classification
by: Dandan Ma, et al.
Published: (2025-04-01) -
Attention Residual Hybrid Network for Unmanned Aerial Vehicles Hyperspectral Image Classification
by: Zhen Zhang, et al.
Published: (2025-01-01) -
Multibranch 3D-Dense Attention Network for Hyperspectral Image Classification
by: Junru Yin, et al.
Published: (2022-01-01)