Open AccessRemote Sensing Images Data Augmentation Based on Style Transfer under the Condition of Few Samples
Author(s) -
Yuchen Jiang,
Bin Zhu,
Bo Xie
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1653/1/012039
Subject(s) - overfitting , computer science , artificial intelligence , domain (mathematical analysis) , convolution (computer science) , image (mathematics) , pattern recognition (psychology) , transfer (computing) , transfer of learning , artificial neural network , texture (cosmology) , computer vision , mathematics , mathematical analysis , parallel computing
To solve the problem that the detection accuracy of remote sensing image is affected by convolution neural network overfitting under the condition of small samples, a data augmentation method based on style transfer is proposed, in which new data is generated from texture of external domain to source domain by using cycle-consistent adversarial networks(CycleGAN). The experiment results show that the accuracy of detection and recognition is improved after adding the generated data to the original data.