INTERACTIVE AUTOENCODERS WITH DEGRADATION CONSTRAINT FOR HYPERSPECTRAL SUPER-RESOLUTION

被引:2
|
作者
Li, Jiaxin [1 ,2 ]
Zheng, Ke [3 ]
Gao, Lianru [1 ]
Ni, Li [1 ]
机构
[1] Chinese Acad Sci, Aerosp Informat Res Inst, Key Lab Computat Opt Imaging Technol, Beijing, Peoples R China
[2] Univ Chinese Acad Sci, Beijing, Peoples R China
[3] Liaocheng Univ, Coll Geog & Environm, Liaocheng, Peoples R China
来源
IGARSS 2023 - 2023 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM | 2023年
基金
国家重点研发计划;
关键词
Deep learning; hyperspectral; multispectral; super-resolution;
D O I
10.1109/IGARSS52108.2023.10282922
中图分类号
P [天文学、地球科学];
学科分类号
07 ;
摘要
Owing to the strong ability of feature extraction and representation, deep learning has exhibited powerful potential in the field of multispectral-aided hyperspectral super-resolution (MS-aided HS-SR). Though great strides have been made by existing methods, their superior performance mainly drives from large training datasets, hence failing to handle the real cases with limited samples. In this article, we propose an unsupervised method inspired by the theory of spectral mixing, which is based solely on one pair of HS-MS correspondence. Specifically, two coupled autoencoders are employed as the backbone of our network, aiming at deriving the latent abundance representations and corresponding endmembers of input HS-MS data. To enrich the feature representations and guide the network learning, we embed an interactive module into the encoder part to enhance the information transmission and design a degradation loss to constrain the target image. Experiments in Chikusei dataset demonstrate the effectiveness of our proposed method.
引用
收藏
页码:7447 / 7450
页数:4
相关论文
共 50 条
  • [21] Subspace Constraint for Single Image Super-Resolution
    Zhang, Yanlin
    Qin, Ding
    Gu, Xiaodong
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2021, PT III, 2021, 12893 : 395 - 407
  • [22] Super-Resolution of Textual Images using Autoencoders for Text Identification
    Pal, Subarno
    Jana, Susovan
    Parekh, Ranjan
    PROCEEDINGS OF 2018 IEEE APPLIED SIGNAL PROCESSING CONFERENCE (ASPCON), 2018, : 153 - 157
  • [23] Degradation learning for unsupervised hyperspectral image super-resolution based on generative adversarial network
    Shaolei Zhang
    Guangyuan Fu
    Hongqiao Wang
    Yuqing Zhao
    Signal, Image and Video Processing, 2021, 15 : 1695 - 1703
  • [24] Degradation learning for unsupervised hyperspectral image super-resolution based on generative adversarial network
    Zhang, Shaolei
    Fu, Guangyuan
    Wang, Hongqiao
    Zhao, Yuqing
    SIGNAL IMAGE AND VIDEO PROCESSING, 2021, 15 (08) : 1695 - 1703
  • [25] RESOLUTION ENHANCEMENT FOR HYPERSPECTRAL IMAGES: A SUPER-RESOLUTION AND FUSION APPROACH
    Kwan, Chiman
    Choi, Joon Hee
    Chan, Stanley
    Zhou, Jin
    Budavari, Bence
    2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2017, : 6180 - 6184
  • [26] Interactive Super-Resolution through Neighbor Embedding
    Pu, Jian
    Zhang, Junping
    Guo, Peihong
    Yuan, Xiaoru
    COMPUTER VISION - ACCV 2009, PT III, 2010, 5996 : 496 - +
  • [27] Hyperspectral image super-resolution using recursive densely convolutional neural network with spatial constraint strategy
    Zhao, Jianwei
    Huang, Taoye
    Zhou, Zhenghua
    NEURAL COMPUTING & APPLICATIONS, 2020, 32 (18): : 14471 - 14481
  • [28] Hyperspectral image super-resolution using recursive densely convolutional neural network with spatial constraint strategy
    Jianwei Zhao
    Taoye Huang
    Zhenghua Zhou
    Neural Computing and Applications, 2020, 32 : 14471 - 14481
  • [29] Hyperspectral Image Super-Resolution via Adaptive Dictionary Learning and Doubl l1Constraint
    Tang, Songze
    Xu, Yang
    Huang, Lili
    Sun, Le
    REMOTE SENSING, 2019, 11 (23)
  • [30] UNSUPERVISED DEEP HYPERSPECTRAL SUPER-RESOLUTION WITH UNREGISTERED IMAGES
    Nie, Jiangtao
    Zhang, Lei
    Wei, Wei
    Ding, Chen
    Zhang, Yanning
    2020 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME), 2020,