Blind Image Separation Method Based on Cascade Generative Adversarial Networks

Jia, Fei; Xu, Jindong; Sun, Xiao; Ni, Mengying

doi:10.3390/app11209416

Cited by 2 publications

(2 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If the value obtained is greater than 0, it is determined that the reconstructed separated image is true; otherwise, it is false, as shown in Equation ( 12), value = tanh(Conv M (ŝ)), (12) where the parameters of the convolution network are set to be the same as those of the generator. The convolution kernel size is k, step size is t, and the tanh activation function is an odd function centered at 0, as shown in Equation (13),…”

Section: Discriminatormentioning

confidence: 99%

“…Ref. [ 13 ] cascaded two layers of GANs based on UNet, UGAN, and PAGAN to implement SCBIS in the case of a few samples, using UGAN for the generation of mixture samples and PAGAN for the separation of images. The resulting cascade GAN focuses more on the insufficient training samples than on the detailed information between pixels at different positions of the image.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Single-Channel Blind Image Separation Based on Transformer-Guided GAN

Jia

Shen

et al. 2023

Sensors

View full text Add to dashboard Cite

Blind source separation (BSS) has been a great challenge in the field of signal processing due to the unknown distribution of the source signal and the mixing matrix. Traditional methods based on statistics and information theory use prior information such as source distribution independence, non-Gaussianity, sparsity, etc. to solve this problem. Generative adversarial networks (GANs) learn source distributions through games without being constrained by statistical properties. However, the current blind image separation methods based on GANs ignores the reconstruction of the structure and details of the separated image, resulting in residual interference source information in the generated results. This paper proposes a Transformer-guided GAN guided by an attention mechanism. Through the adversarial training of the generator and the discriminator, U-shaped Network (UNet) is used to fuse the convolutional layer features to reconstruct the structure of the separated image, and Transformer is used to calculate the position attention and guide the detailed information. We validate our method with quantitative experiments, showing that it outperforms previous blind image separation algorithms in terms of PSNR and SSIM.

show abstract

Section: Discriminatormentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Single-Channel Blind Image Separation Based on Transformer-Guided GAN

Jia

Shen

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

Underwater Object Classification Method Based on Depthwise Separable Convolution Feature Fusion in Sonar Images

2022

View full text Add to dashboard Cite

In order to improve the accuracy of underwater object classification, according to the characteristics of sonar images, a classification method based on depthwise separable convolution feature fusion is proposed. Firstly, Markov segmentation is used to segment the highlight and shadow regions of the object to avoid the loss of information caused by simultaneous segmentation. Secondly, depthwise separable convolution is used to learn the deep information of images for feature extraction, which produces less network computation. Thirdly, features of highlight and shadow regions are fused by the parallel network structure, and pyramid pooling is added to extract the multi-scale information. Finally, the full connection layers are used to achieve object classification through the Softmax function. Experiments are conducted on simulated and real data. Results show that the method proposed in this paper achieve superior performance compared with other models, and it also has certain flexibility.

show abstract

Blind Image Separation Method Based on Cascade Generative Adversarial Networks

Cited by 2 publications

References 27 publications

Single-Channel Blind Image Separation Based on Transformer-Guided GAN

Single-Channel Blind Image Separation Based on Transformer-Guided GAN

Underwater Object Classification Method Based on Depthwise Separable Convolution Feature Fusion in Sonar Images

Contact Info

Product

Resources

About