# Few-Shot Hyperspectral Image Classification With Unknown Classes Using Multitask Deep Learning

arXiv: https://arxiv.org/abs/2009.03508 · HTML: https://mlsanity.com/paper/2009.03508/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Sep 2020.

## Built on by (most cited first, 13 of 13)

- [SpectralDiff: A Generative Framework for Hyperspectral Image Classification with Diffusion Models](https://mlsanity.com/paper/2304.05961/) (2023)
- [Object Detection in Hyperspectral Image via Unified Spectral-Spatial Feature Aggregation](https://mlsanity.com/paper/2306.08370/) (2023)
- [Robust Self-Ensembling Network for Hyperspectral Image Classification](https://mlsanity.com/paper/2104.03765/) (2021)
- [Transformer-Driven Active Transfer Learning for Cross-Hyperspectral Image Classification](https://mlsanity.com/paper/2411.18115/) (2024)
- [Instance Selection Mechanisms for Human-in-the-Loop Systems in Few-Shot Learning](https://mlsanity.com/paper/2207.06835/) (2022)
- [Deep Feature Gaussian Processes for Single-Scene Aerosol Optical Depth Reconstruction](https://mlsanity.com/paper/2405.17262/) (2024)
- [Towards Deep and Efficient: A Deep Siamese Self-Attention Fully Efficient Convolutional Network for Change Detection in VHR Images](https://mlsanity.com/paper/2108.08157/) (2021)
- [Nonnegative-Constrained Joint Collaborative Representation with Union Dictionary for Hyperspectral Anomaly Detection](https://mlsanity.com/paper/2203.10030/) (2022)
- [Uncertainty-Aware Hourly Air Temperature Mapping at 2 km Resolution via Physics-Guided Deep Learning](https://mlsanity.com/paper/2509.12329/) (2025)
- [Land Cover Image Classification](https://mlsanity.com/paper/2401.09607/) (2024)
- [HOpenCls: Training Hyperspectral Image Open-Set Classifiers in Their Living Environments](https://mlsanity.com/paper/2502.15163/) (2025)
- [Few-shot Unknown Class Discovery of Hyperspectral Images with Prototype Learning and Clustering](https://mlsanity.com/paper/2508.18075/) (2025)
- [Multitask Learning for Earth Observation Data Classification with Hybrid Quantum Network](https://mlsanity.com/paper/2601.22195/) (2026)

## Abstract (arXiv)

Current hyperspectral image classification assumes that a predefined classification system is closed and complete, and there are no unknown or novel classes in the unseen data. However, this assumption may be too strict for the real world. Often, novel classes are overlooked when the classification system is constructed. The closed nature forces a model to assign a label given a new sample and may lead to overestimation of known land covers (e.g., crop area). To tackle this issue, we propose a multitask deep learning method that simultaneously conducts classification and reconstruction in the open world (named MDL4OW) where unknown classes may exist. The reconstructed data are compared with the original data; those failing to be reconstructed are considered unknown, based on the assumption that they are not well represented in the latent features due to the lack of labels. A threshold needs to be defined to separate the unknown and known classes; we propose two strategies based on the extreme value theory for few-shot and many-shot scenarios. The proposed method was tested on real-world hyperspectral images; state-of-the-art results were achieved, e.g., improving the overall accuracy by 4.94% for the Salinas data. By considering the existence of unknown classes in the open world, our method achieved more accurate hyperspectral image classification, especially under the few-shot context.