Remote Sensing Image Synthesis via Graphical Generative Adversarial Networks

Wang, Guangxing; Dong, Guoshuai; Li, Hui; Han, Lirong; Tao, Xuanwen; Ren, Peng

doi:10.1109/igarss.2019.8898915

Cited by 7 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For sample augmentation, CGAN [41] integrates added conditional constraints into GANs, facilitating the generation of category-specific images. However, this approach suffers from issues of limited diversity in generated images and recurring problems of pattern collapse [42,43]. Following this, seminal models like Pix2Pix [44] and CycleGAN [45] were developed.…”

Section: Sample Generationmentioning

confidence: 99%

Semantic-Layout-Guided Image Synthesis for High-Quality Synthetic-Aperature Radar Detection Sample Generation

Kuang,

Ma,

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

With the widespread application and functional complexity of deep neural networks (DNNs), the demand for training samples is increasing. This elevated requirement also extends to DNN-based SAR object detection. Most public SAR object detection datasets are oriented to marine targets such as ships, while data sets oriented to land targets are relatively rare, though they are an effective way to improve the land object detection capability of deep models through SAR sample generation. In this paper, a synthesis generation collaborative SAR sample augmentation framework is proposed to achieve flexible and diverse high-quality sample augmentation. First, a semantic-layout-guided image synthesis strategy is proposed to generate diverse detection samples. The issues of object location rationality and object layout diversity are also addressed. Meanwhile, a pix2pixGAN network guided by layout maps is utilized to achieve diverse background augmentation. Second, a progressive training strategy of diffusion models is proposed to achieve semantically controllable SAR sample generation to further improve the diversity of scene clutter. Finally, a sample cleaning method considering distribution migration and network filtering is employed to further improve the quality of detection samples. The experimental results show that this semantic synthesis generation method can outperform existing sample augmentation methods, leading to a comprehensive improvement in the accuracy metrics of classical detection networks.

show abstract

Section: Sample Generationmentioning

confidence: 99%

Semantic-Layout-Guided Image Synthesis for High-Quality Synthetic-Aperature Radar Detection Sample Generation

Kuang,

Ma,

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Besides, remote sensing images usually contain targets that are structurally dependent on each other. From this point of view, [15] propose to use Graphical GAN calculate latent relationships for image generation, but images generated by it are usually with blurs. Some previous works [16,17] add pixel-wise attentions to capture structural features for remote sensing image generation.…”

Section: Introductionmentioning

confidence: 99%

Skip Attention GAN for Remote Sensing Image Synthesis

Deng

Zhang

Yao

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

High-quality remote sensing images are difficult to obtain due to limited conditions and high cost for data acquisition. With the development of machine vision and deep learning, some image generation methods (e.g., GANs) are introduced into this field, but it's still hard to generate images with good texture details and structural dependencies. We establish Skip Attention Mechanism to deal with this problem, which learns dependencies between local points on low-resolution feature maps, and then upsample the attention map and combine it with high-resolution feature maps. With this method, longrange dependencies learned from low-resolution are used for generating remote sensing images with more structural details. We name this method as Skip Attention GAN, which is the first method applying cross-scale attention mechanism for unsupervised remote sensing image generation. Experiments show that our method outperforms previous methods under several metrics. Visual and ablation results of attention layers show that Skip Attention has learned long-distance structural dependencies between similar targets.

show abstract

Cloud Removal on Satellite Image using Transfer Learning based Generative Adversarial Network

Ahn

Kim

et al. 2020

2020 International Conference on Information and Communication Technology Convergence (ICTC)

View full text Add to dashboard Cite

Remote Sensing Image Synthesis via Graphical Generative Adversarial Networks

Cited by 7 publications

References 4 publications

Semantic-Layout-Guided Image Synthesis for High-Quality Synthetic-Aperature Radar Detection Sample Generation

Semantic-Layout-Guided Image Synthesis for High-Quality Synthetic-Aperature Radar Detection Sample Generation

Skip Attention GAN for Remote Sensing Image Synthesis

Cloud Removal on Satellite Image using Transfer Learning based Generative Adversarial Network

Contact Info

Product

Resources

About