Transformer-Based Masked Autoencoder With Contrastive Loss for Hyperspectral Image Classification

高光谱成像 计算机科学 人工智能 自编码 模式识别(心理学) 上下文图像分类 遥感 计算机视觉 图像(数学) 地质学 人工神经网络
作者
Xianghai Cao,Haifeng Lin,Shuaixu Guo,Tao Xiong,Licheng Jiao
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:61: 1-12 被引量:26
标识
DOI:10.1109/tgrs.2023.3315678
摘要

Recent years, in order to solve the problem of lacking accurately labeled hyperspectral image data, self-supervised learning has become an effective method for hyperspectral image classification. The core idea of self-supervised learning is to define a pretext task which helps to train the model without the labels. By exploiting both the information of the labeled and unlabeled samples, self-supervised learning shows enormous potential to handle many different tasks in the field of hyperspectral image processing. Among the vast amount of self-supervised methods, contrastive learning and masked autoencoder are well known because of their impressive performance. This article proposes a Transformer based masked autoencoder using contrastive learning (TMAC), which tries to combine these two methods and improve the performance further. TMAC has two branches, the first branch has an encoder-decoders structure, it has an encoder to capture the latent image representation of the masked hyperspectral image and two decoders where the pixel decoder aims to reconstruct the hyperspectral image at pixel-level and the feature decoder is built to extract the high-level feature of the reconstructed image. The second branch consists of a momentum encoder and a standard projection head to embed the image into the feature space. Then, by combining the output of feature decoder and the embedding vectors via contrastive learning to enhance the model's classification performance. According to the experiments, our model shows powerful feature extraction capability and gets outstanding results on hyperspectral image datasets.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
2秒前
今后应助老乔采纳,获得10
4秒前
小蘑菇应助lunjianchi采纳,获得10
4秒前
刘佳冉完成签到,获得积分10
5秒前
5秒前
6秒前
淡然善斓完成签到,获得积分10
7秒前
要减肥的惜萱完成签到,获得积分10
8秒前
行路人发布了新的文献求助20
8秒前
整齐冬瓜完成签到,获得积分10
9秒前
xlxl发布了新的文献求助30
9秒前
Hello应助峰1992采纳,获得10
10秒前
11秒前
12秒前
Akim应助upsoar采纳,获得10
12秒前
12秒前
12秒前
LZQ应助wjw采纳,获得10
13秒前
FashionBoy应助孟古采纳,获得10
13秒前
科研通AI2S应助demian采纳,获得10
15秒前
踏雪飞鸿发布了新的文献求助10
16秒前
18秒前
19秒前
沈DJ发布了新的文献求助10
19秒前
spp完成签到 ,获得积分0
21秒前
23秒前
和谐的巨人完成签到 ,获得积分10
23秒前
重要鑫磊发布了新的文献求助10
25秒前
upsoar发布了新的文献求助10
28秒前
28秒前
ABEDO完成签到 ,获得积分10
29秒前
眼睛大依霜完成签到,获得积分20
30秒前
30秒前
30秒前
可爱的函函应助重要鑫磊采纳,获得10
32秒前
33秒前
Nuckylin发布了新的文献求助10
34秒前
寸光发布了新的文献求助10
35秒前
37秒前
乙醇发布了新的文献求助10
37秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
Immigrant Incorporation in East Asian Democracies 600
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3967419
求助须知:如何正确求助?哪些是违规求助? 3512730
关于积分的说明 11164792
捐赠科研通 3247704
什么是DOI,文献DOI怎么找? 1793978
邀请新用户注册赠送积分活动 874785
科研通“疑难数据库(出版商)”最低求助积分说明 804517