Saved in:
Bibliographic Details
Main Authors: Liu, Quanwei, Dong, Yanni, Huang, Tao, Zhang, Lefei, Du, Bo
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.01673
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914773386395648
author Liu, Quanwei
Dong, Yanni
Huang, Tao
Zhang, Lefei
Du, Bo
author_facet Liu, Quanwei
Dong, Yanni
Huang, Tao
Zhang, Lefei
Du, Bo
contents 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}.
format Preprint
id arxiv_https___arxiv_org_abs_2404_01673
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Universal Knowledge Embedded Contrastive Learning Framework for Hyperspectral Image Classification
Liu, Quanwei
Dong, Yanni
Huang, Tao
Zhang, Lefei
Du, Bo
Computer Vision and Pattern Recognition
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}.
title A Universal Knowledge Embedded Contrastive Learning Framework for Hyperspectral Image Classification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.01673