A Universal Knowledge Embedded Contrastive Learning Framework for Hyperspectral Image Classification

TL;DR

This paper introduces a versatile contrastive learning framework, KnowCL, for hyperspectral image classification that improves generalization and realistic evaluation across supervised, unsupervised, and semi-supervised settings.

Contribution

It presents a universal framework compatible with various backbones, a new data processing pipeline, and an adaptive loss function to enhance HSI classification performance.

Findings

Framework closes gap between pocket models and vision backbones

Compatible with all backbone types and exploits labeled/unlabeled data

Shows promising results in diverse HSI classification scenarios

Abstract

Hyperspectral image (HSI) classification techniques have been intensively studied and a variety of models have been developed. However, these HSI classification models are confined to pocket models and unrealistic ways of dataset partitioning. The former limits the generalization performance of the model and the latter is partitioned leading to inflated model evaluation metrics, which results in plummeting model performance in the real world. Therefore, we propose a universal knowledge embedded contrastive learning framework (KnowCL) for supervised, unsupervised, and semisupervised HSI classification, which largely closes the gap between HSI classification models between pocket models and standard vision backbones. We present a new HSI processing pipeline in conjunction with a range of data transformation and augmentation techniques that provide diverse data representations and realistic data partitioning. The proposed framework based on this pipeline is compatible with all kinds of backbones and can fully exploit labeled and unlabeled samples with the expected training time. Furthermore, we design a new loss function, which can adaptively fuse the supervised loss and unsupervised loss, enhancing the learning performance. This proposed new classification paradigm shows great potential in exploring for HSI classification technology. The code can be accessed at \url{https://github.com/quanweiliu/KnowCL}.