Year: 2025
Type: conference-paper
Abstract: 2D convolutional neural networks (CNNs) have attracted significant attention for hyperspectral image superresolution tasks. However, a key limitation is their reliance on local neighborhoods, which leads to a lack of global contextual understanding. Moreover, band correlation and data scarcity continue to limit their performance. To mitigate these issues, we introduce DACN, a dual-attention convolutional network for hyperspectral image super-resolution. Specifically, the model first employs augmented convolutions, integrating multi-head attention to effectively capture both local and global feature dependencies. Next, we infer separate attention maps for the channel and spatial dimensions to determine where to focus across different channels and spatial positions. Furthermore, a custom optimized loss function is proposed that combines L2 regularization with spatial-spectral gradient loss to ensure accurate spectral fidelity. Experimental results on two hyperspectral datasets demonstrate that the combination of multihead attention and channel attention outperforms either attention mechanism used individually. The source codes are publicly available at: https://github.com/Usman1021/dual-attention.
Authors: Usman Muhammad, Jorma Laaksonen
Institution: Aalto University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funders: European Commission, NextGenerationEU
OpenAlex ID: W4417052187