# Unsupervised Feature Learning by Autoencoder and Prototypical Contrastive Learning for Hyperspectral Classification

arXiv: https://arxiv.org/abs/2009.00953 · HTML: https://mlsanity.com/paper/2009.00953/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Sep 2020.

## Built on by (most cited first, 9 of 9)

- [Multimodal Data Integration for Oncology in the Era of Deep Neural Networks: A Review](https://mlsanity.com/paper/2303.06471/) (2023)
- [Graph Neural Networks: Methods, Applications, and Opportunities](https://mlsanity.com/paper/2108.10733/) (2021)
- [Bridge to Target Domain by Prototypical Contrastive Learning and Label Confusion: Re-explore Zero-Shot Learning for Slot Filling](https://mlsanity.com/paper/2110.03572/) (2021)
- [A Machine Learning Enhanced Approach for Automated Sunquake Detection in Acoustic Emission Maps](https://mlsanity.com/paper/2212.06717/) (2022)
- [CEU-Net: Ensemble Semantic Segmentation of Hyperspectral Images Using Clustering](https://mlsanity.com/paper/2203.04873/) (2022)
- [A Universal Knowledge Embedded Contrastive Learning Framework for Hyperspectral Image Classification](https://mlsanity.com/paper/2404.01673/) (2024)
- [Cross-View-Prediction: Exploring Contrastive Feature for Hyperspectral Image Classification](https://mlsanity.com/paper/2203.07000/) (2022)
- [Enhancing Hyperspectral Image Prediction with Contrastive Learning in Low-Label Regime](https://mlsanity.com/paper/2410.07790/) (2024)
- [From Pixels to Images: A Structural Survey of Deep Learning Paradigms in Remote Sensing Image Semantic Segmentation](https://mlsanity.com/paper/2505.15147/) (2025)

## Abstract (arXiv)

Unsupervised learning methods for feature extraction are becoming more and more popular. We combine the popular contrastive learning method (prototypical contrastive learning) and the classic representation learning method (autoencoder) to design an unsupervised feature learning network for hyperspectral classification. Experiments have proved that our two proposed autoencoder networks have good feature learning capabilities by themselves, and the contrastive learning network we designed can better combine the features of the two to learn more representative features. As a result, our method surpasses other comparison methods in the hyperspectral classification experiments, including some supervised methods. Moreover, our method maintains a fast feature extraction speed than baseline methods. In addition, our method reduces the requirements for huge computing resources, separates feature extraction and contrastive learning, and allows more researchers to conduct research and experiments on unsupervised contrastive learning.