Attentive-Adaptive Network for Hyperspectral Images Classification With Noisy Labels

被引:16
作者
Wang, Leiquan [1 ,2 ]
Zhu, Tongchuan [3 ]
Kumar, Neeraj [4 ,5 ,6 ]
Li, Zhongwei [7 ]
Wu, Chunlei [3 ]
Zhang, Peiying [1 ,2 ]
机构
[1] China Univ Petr East China, Qingdao Inst Software, Coll Comp Sci & Technol, Qingdao 266580, Peoples R China
[2] Xidian Univ, State Key Lab Integrated Serv Networks, Xian 710071, Peoples R China
[3] China Univ Petr, Qingdao Inst Software, Coll Comp Sci & Technol, Qingdao 266580, Peoples R China
[4] Thapar Inst Engn & Technol, Dept Comp Sci & Engn, Patiala 147004, Punjab, India
[5] Univ Petr & Energy Studies, Sch Comp Sci, Dehra Dun 248007, Uttarakhand, India
[6] Lebanese Amer Univ, Dept Elect & Comp Engn, Beirut 11022801, Lebanon
[7] China Univ Petr East China, Coll Oceanog & Space Informat, Qingdao 266580, Peoples R China
来源
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING | 2023年 / 61卷
基金
中国国家自然科学基金;
关键词
Noise measurement; Training; Feature extraction; Hyperspectral imaging; Adaptation models; Noise robustness; Deep learning; hyperspectral images classification; noisy labels;
D O I
10.1109/TGRS.2023.3254159
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
With the development of deep neural networks, hyperspectral image (HSI) classification systems have achieved a significant improvement. These systems require numerous and accurately labeled hyperspectral data to be adequately trained. However, noisy labels are inherent in real-world hyperspectral systems, resulting in unreliable decisions. To handle noisy labels in hyperspectral classification, an end-to-end attentive-adaptive network (AAN) is proposed for robust HSI classification training. The goal is to build a classifier with strong generalization capabilities that can be applied to both clean and noisy training sets without explicit noise label pretreatment. Specifically, a spectral stem network with a nonadjacent shortcut is exploited initially to redistribute the sensitive layers for noisy labels to achieve robust spectral representation. Then, a group-shuffle attention module is proposed to capture the discriminative and robust spatial-spectral features in the presence of noisy labels. Finally, an adaptive noise-robust loss (ANRL) function is developed to fight against noisy labels by learning a parameter to balance the normalized cross entropy (NCE) and reverse cross entropy (RCE). Experimental results on three HSI benchmark datasets with simulated noisy labels demonstrate the effectiveness of AAN on HSI classification.
引用
收藏
页数:14
相关论文
共 42 条
[1]   Classification of Hyperspectral Images With Regularized Linear Discriminant Analysis [J].
Bandos, Tatyana V. ;
Bruzzone, Lorenzo ;
Camps-Valls, Gustavo .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2009, 47 (03) :862-873
[2]   3-D Deep Learning Approach for Remote Sensing Image Classification [J].
Ben Hamida, Amina ;
Benoit, Alexandre ;
Lambert, Patrick ;
Ben Amar, Chokri .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2018, 56 (08) :4420-4434
[3]   Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks [J].
Chen, Yushi ;
Jiang, Hanlu ;
Li, Chunyang ;
Jia, Xiuping ;
Ghamisi, Pedram .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2016, 54 (10) :6232-6251
[4]   Fusion of Dual Spatial Information for Hyperspectral Image Classification [J].
Duan, Puhong ;
Ghamisi, Pedram ;
Kang, Xudong ;
RastiO, Behnood ;
Li, Shutao ;
Gloaguen, Richard .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2021, 59 (09) :7726-7738
[5]  
Feng L, 2020, PROCEEDINGS OF THE TWENTY-NINTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, P2206
[6]   SpectralFormer: Rethinking Hyperspectral Image Classification With Transformers [J].
Hong, Danfeng ;
Han, Zhu ;
Yao, Jing ;
Gao, Lianru ;
Zhang, Bing ;
Plaza, Antonio ;
Chanussot, Jocelyn .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
[7]   Deep Convolutional Neural Networks for Hyperspectral Image Classification [J].
Hu, Wei ;
Huang, Yangyu ;
Wei, Li ;
Zhang, Fan ;
Li, Hengchao .
JOURNAL OF SENSORS, 2015, 2015
[8]   Hyperspectral Image Classification in the Presence of Noisy Labels [J].
Jiang, Junjun ;
Ma, Jiayi ;
Wang, Zheng ;
Chen, Chen ;
Liu, Xianming .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2019, 57 (02) :851-865
[9]   Multilayer Spectral-Spatial Graphs for Label Noisy Robust Hyperspectral Image Classification [J].
Jiang, Junjun ;
Ma, Jiayi ;
Liu, Xianming .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 33 (02) :839-852
[10]   Detection and Correction of Mislabeled Training Samples for Hyperspectral Image Classification [J].
Kang, Xudong ;
Duan, Puhong ;
Xiang, Xuanlin ;
Li, Shutao ;
Benediktsson, Jon Atli .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2018, 56 (10) :5673-5686