Deep Architectures Fail to Generalize: A Lightweight Alternative for Agricultural Domain Transfer in Hyperspectral Images
Open Access
Abstract
We present a novel framework for hyperspectral satellite image classification that explicitly balances spatial nearness with spectral similarity. The proposed method is trained on closed-set datasets, and it generalizes well to open-set agricultural scenarios that include both class distribution shifts and presence of novel and absence of known classes. This scenario is reflective of real-world agricultural conditions, where geographic regions, crop types, and seasonal dynamics vary widely and labeled data are scarce and expensive. The input data are projected onto a lower-dimensional spectral manifold, and a pixel-wise classifier generates an initial class probability saliency map. A kernel-based spectral-spatial weighting strategy fuses the spatial-spectral features. The proposed approach improves the classification accuracy by – over spectral-only models on benchmark datasets. Incorporating an additional unsupervised learning refinement step further improves accuracy, surpassing several recent state-of-the-art methods. Requiring only 1– labeled training data and at most two tuneable parameters, the framework operates with minimal computational overhead, qualifying it as a data-efficient and scalable few-shot learning solution. Recent deep architectures although exhibit high accuracy under data rich conditions, often show limited transferability under low-label, open-set agricultural conditions. We demonstrate transferability to new domains—including unseen crop classes (e.g., paddy), seasons, and regions (e.g., Piedmont, Italy)—without re-training. Rice paddy fields play a pivotal role in global food security but are also a significant contributor to greenhouse gas emissions, especially methane, and extent mapping is very critical. This work presents a novel perspective on hyperspectral classification and open-set adaptation, suited for sustainable agriculture with limited labels and low-resource domain generalization.
Keywords
All Related Versions
Funding Information
- UrbanKisaan Inc.
This publication has 54 references indexed in Scilit:
- A comprehensive survey for Hyperspectral Image Classification: The evolution from conventional to transformers and Mamba modelsNeurocomputing, 2025
- An unsupervised domain adaptation deep learning method for spatial and temporal transferable crop type mapping using Sentinel-2 imageryISPRS Journal of Photogrammetry and Remote Sensing, 2023
- Remote sensing for agricultural applications: A meta-reviewRemote Sensing of Environment, 2020
- Algorithms for semantic segmentation of multispectral remote sensing imagery using deep learningISPRS Journal of Photogrammetry and Remote Sensing, 2018
- PCA, Kernel PCA and Dimensionality Reduction in Hyperspectral Images2017
- Explaining nonlinear classification decisions with deep Taylor decompositionPattern Recognition, 2017
- Detecting the effects of hydrocarbon pollution in the Amazon forest using hyperspectral satellite imagesEnvironmental Pollution, 2015
- CORINE Land Cover and Land Cover Change Products2014
- TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and ContextInternational Journal of Computer Vision, 2007
- Principal component analysisChemometrics and Intelligent Laboratory Systems, 1987