Pair-Wise Similarity Knowledge Distillation for RSI Scene Classification

被引:10
作者
Zhao, Haoran [1 ,2 ]
Sun, Xin [1 ,2 ,3 ]
Gao, Feng [1 ,2 ]
Dong, Junyu [1 ,2 ]
机构
[1] Ocean Univ China, Coll Informat Sci & Engn, Haide Coll, Qingdao 266100, Peoples R China
[2] Ocean Univ China, Inst Adv Ocean Study, Qingdao 266100, Peoples R China
[3] Tech Univ Munich, Dept Aerosp & Geodesy, D-80333 Munich, Germany
基金
中国国家自然科学基金;
关键词
knowledge distillation; imaging science; scene classification; geosciences; convolutional neural network; NETWORK;
D O I
10.3390/rs14102483
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Remote sensing image (RSI) scene classification aims to identify the semantic categories of remote sensing images based on their contents. Owing to the strong learning capability of deep convolutional neural networks (CNNs), RSI scene classification methods based on CNNs have drawn much attention and achieved remarkable performance. However, such outstanding deep neural networks are usually computationally expensive and time-consuming, making them impossible to apply on resource-constrained edge devices, such as the embedded systems used on drones. To tackle this problem, we introduce a novel pair-wise similarity knowledge distillation method, which could reduce the model complexity while maintaining satisfactory accuracy, to obtain a compact and efficient deep neural network for RSI scene classification. Different from the existing knowledge distillation methods, we design a novel distillation loss to transfer the valuable discriminative information, which could reduce the within-class variations and restrain the between-class similarity, from the cumbersome model to the compact model. This method could obtain the compact student model with higher performance compared with existing knowledge distillation methods in RSI scene classification. To be specific, we distill the probability outputs between sample pairs with the same label and match the probability outputs between the teacher and student models. Experiments on three public benchmark datasets for RSI scene classification, i.e., AID, UCMerced, and NWPU-RESISC datasets, verify that the proposed method could effectively distill the knowledge and result in a higher performance.
引用
收藏
页数:17
相关论文
共 43 条
[31]   Scene Classification With Recurrent Attention of VHR Remote Sensing Images [J].
Wang, Qi ;
Liu, Shaoteng ;
Chanussot, Jocelyn ;
Li, Xuelong .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2019, 57 (02) :1155-1167
[32]   AID: A Benchmark Data Set for Performance Evaluation of Aerial Scene Classification [J].
Xia, Gui-Song ;
Hu, Jingwen ;
Hu, Fan ;
Shi, Baoguang ;
Bai, Xiang ;
Zhong, Yanfei ;
Zhang, Liangpei ;
Lu, Xiaoqiang .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2017, 55 (07) :3965-3981
[33]   Quantization Networks [J].
Yang, Jiwei ;
Shen, Xu ;
Xing, Jun ;
Tian, Xinmei ;
Li, Houqiang ;
Deng, Bing ;
Huang, Jianqiang ;
Hua, Xian-sheng .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :7300-7308
[34]  
Yang Yi, 2010, SIGSPATIAL GIS, P270, DOI DOI 10.1145/1869790.1869829
[35]  
Zagoruyko S., 2017, P INT C LEARN REPR I
[36]   Scene Classification via a Gradient Boosting Random Convolutional Network Framework [J].
Zhang, Fan ;
Du, Bo ;
Zhang, Liangpei .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2016, 54 (03) :1793-1802
[37]   Saliency-Guided Unsupervised Feature Learning for Scene Classification [J].
Zhang, Fan ;
Du, Bo ;
Zhang, Liangpei .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2015, 53 (04) :2175-2184
[38]   Adversarial co-distillation learning for image recognition [J].
Zhang, Haoran ;
Hu, Zhenzhen ;
Qin, Wei ;
Xu, Mingliang ;
Wang, Meng .
PATTERN RECOGNITION, 2021, 111
[39]   Remote Sensing Image Scene Classification with Noisy Label Distillation [J].
Zhang, Rui ;
Chen, Zhenghao ;
Zhang, Sanxing ;
Song, Fei ;
Zhang, Gang ;
Zhou, Quancheng ;
Lei, Tao .
REMOTE SENSING, 2020, 12 (15)
[40]   Knowledge distillation via instance-level sequence learning [J].
Zhao, Haoran ;
Sun, Xin ;
Dong, Junyu ;
Dong, Zihe ;
Li, Qiong .
KNOWLEDGE-BASED SYSTEMS, 2021, 233