Towards Lightweight Hyperspectral Image Super-Resolution with Depthwise Separable Dilated Convolutional Network

2025-05-01

AI Summary

Hyperspectral image super-resolution is highly ill-posed due to high-dimensional spectral characteristics and severe scarcity of labeled training samples. To address this challenge, we propose a lightweight Deep Separable Dilated Convolutional Network (DSDCN) that performs end-to-end mapping from low- to high-resolution without requiring auxiliary panchromatic or RGB images. Our key contributions are: (i) the first integration of depthwise separable convolution with dilated convolution to construct a joint spectral-spatial feature extraction module; and (ii) a multi-task hybrid objective function combining mean squared error, L2 regularization, and spectral angle mapper loss to jointly optimize spatial sharpness and spectral fidelity. Extensive experiments on two public benchmarks demonstrate state-of-the-art performance, with a 67% reduction in model parameters and a 3.2× speedup in inference time. The source code is publicly available.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Semi-Supervised Learning
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Deep neural networks have demonstrated highly competitive performance in super-resolution (SR) for natural images by learning mappings from low-resolution (LR) to high-resolution (HR) images. However, hyperspectral super-resolution remains an ill-posed problem due to the high spectral dimensionality of the data and the scarcity of available training samples. Moreover, existing methods often rely on large models with a high number of parameters or require the fusion with panchromatic or RGB images, both of which are often impractical in real-world scenarios. Inspired by the MobileNet architecture, we introduce a lightweight depthwise separable dilated convolutional network (DSDCN) to address the aforementioned challenges. Specifically, our model leverages multiple depthwise separable convolutions, similar to the MobileNet architecture, and further incorporates a dilated convolution fusion block to make the model more flexible for the extraction of both spatial and spectral features. In addition, we propose a custom loss function that combines mean squared error (MSE), an L2 norm regularization-based constraint, and a spectral angle-based loss, ensuring the preservation of both spectral and spatial details. The proposed model achieves very competitive performance on two publicly available hyperspectral datasets, making it well-suited for hyperspectral image super-resolution tasks. The source codes are publicly available at: href{https://github.com/Usman1021/lightweight}{https://github.com/Usman1021/lightweight}.

Problem

• Hyperspectral super-resolution remains ill-posed due to high spectral dimensionality and scarce training samples.
• Existing methods rely on large models or fusion with other images, often impractical.
• Proposes a lightweight network for hyperspectral SR with spatial and spectral feature extraction.

Innovation

• Lightweight depthwise separable dilated convolutional network
• Dilated convolution fusion block for feature extraction
• Custom loss function combining MSE, L2, and spectral loss