.png){kind=icon}
返回
Regularized Masked Auto-Encoder for Semi-Supervised Hyperspectral Image Classification
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2024.3509720.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
As the most prevalent self-supervised representation learning (SSRL) model, the masked auto-encoder (MAE) has been gradually investigated in semi-supervised hyperspectral image classification (SHIC). However, the majority of the current approaches augment MAE merely from the application perspective or by introducing a weak regularization term, and do not comprehensively consider the challenges posed by the high intraclass variances and interclass similarities that often appear in hyperspectral image (HSI) data. In this article, we present a regularized MAE (RMAE) to address the aforementioned problems. Specifically, within the framework of MAE, we introduce a self-designed induced transformer block, using a small number of visible patches to learn the embeddings of patches with larger receptive fields. The learned embeddings are used to reconstruct the corresponding patches and an induced reconstruction loss is calculated. This strategy creates a much harder task for masked image modeling (MIM), and the induced transformer block is lightweight and imposes negligible computational burden overhead the underlying MAE framework. In addition, by rethinking the masking operations, we develop a masked convolutional neural network (MCNN), uncovering the principle of MAE and affirming the efficacy of RMAE. Finally, we present two metrics: the mean intraclass distance, and the mean interclass distance. Based on the metrics we give two criteria to evaluate the performance of an SSRL model, providing a new coordinate for the research in SSRL-based SHIC. Experiments conducted on four publicly accessible datasets show that RMAE outperforms state-of-the-art methods. The source code was powered by Jupyter and released at https://github.com/swiftest/RMAE.
Keyword:
Transformers
Feature extraction
Training
Three-dimensional displays
Convolution
Tuning
Sun
Representation learning
Iterative methods
Hyperspectral imaging
Induced transformer
masked image modeling (MIM)
regularized masked auto-encoder (MAE)
self-supervised representation learning (SSRL)
semi-supervised hyperspectral image classification (SHIC)
期刊
IF:
8.6
论文数:
2.2W
被引数:
10.7W
机构
引用论文
.png){kind=icon}
分享收藏Semi-Supervised Multiscale Dynamic Graph Convolution Network for Hyperspectral Image Classification用于高光谱图像分类的半监督多尺度动态图卷积网络
PREAI
分享收藏A review on graph-based semi-supervised learning methods for hyperspectral image classification基于图的半监督学习高光谱图像分类方法综述
OAAI
OAAI分享收藏
查看更多内容