SAM-GAN: Self-Attention supporting Multi-stage Generative Adversarial Networks for text-to-image synthesis

2021 ◽  
Vol 138 ◽  
pp. 57-67
Author(s):  
Dunlu Peng ◽  
Wuchen Yang ◽  
Cong Liu ◽  
Shuairui Lü
Keyword(s):  
Image Synthesis ◽  
Generative Adversarial Networks ◽  
Adversarial Networks ◽  
Multi Stage

scholarly journals mustGAN: multi-stream Generative Adversarial Networks for MR Image Synthesis

2021 ◽  
pp. 101944
Author(s):  
Mahmut Yurt ◽  
Salman U.H. Dar ◽  
Aykut Erdem ◽  
Erkut Erdem ◽  
Kader K Oguz ◽  
...  
Keyword(s):  
Image Synthesis ◽  
Generative Adversarial Networks ◽  
Mr Image ◽  
Adversarial Networks

scholarly journals Breast Ultrasound Image Synthesis using Deep Convolutional Generative Adversarial Networks

Diagnostics ◽  
2019 ◽  
Vol 9 (4) ◽  
pp. 176 ◽  
Author(s):  
Tomoyuki Fujioka ◽  
Mio Mori ◽  
Kazunori Kubota ◽  
Yuka Kikuchi ◽  
Leona Katsuta ◽  
...  
Keyword(s):  
Ultrasound Image ◽  
Image Synthesis ◽  
Breast Ultrasound ◽  
Generative Adversarial Networks ◽  
Ultrasound Images ◽  
Clinical Value ◽  
Adversarial Networks ◽  
Significant Difference ◽  
Definition Of ◽  
The Masses

Deep convolutional generative adversarial networks (DCGANs) are newly developed tools for generating synthesized images. To determine the clinical utility of synthesized images, we generated breast ultrasound images and assessed their quality and clinical value. After retrospectively collecting 528 images of 144 benign masses and 529 images of 216 malignant masses in the breasts, synthesized images were generated using a DCGAN with 50, 100, 200, 500, and 1000 epochs. The synthesized (n = 20) and original (n = 40) images were evaluated by two radiologists, who scored them for overall quality, definition of anatomic structures, and visualization of the masses on a five-point scale. They also scored the possibility of images being original. Although there was no significant difference between the images synthesized with 1000 and 500 epochs, the latter were evaluated as being of higher quality than all other images. Moreover, 2.5%, 0%, 12.5%, 37.5%, and 22.5% of the images synthesized with 50, 100, 200, 500, and 1000 epochs, respectively, and 14% of the original images were indistinguishable from one another. Interobserver agreement was very good (|r| = 0.708–0.825, p < 0.001). Therefore, DCGAN can generate high-quality and realistic synthesized breast ultrasound images that are indistinguishable from the original images.

scholarly journals Text to Realistic Image Generation with Attentional Concatenation Generative Adversarial Networks

2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Linyan Li ◽  
Yu Sun ◽  
Fuyuan Hu ◽  
Tao Zhou ◽  
Xuefeng Xi ◽  
...  
Keyword(s):  
High Resolution ◽  
Image Synthesis ◽  
Semantic Space ◽  
Generative Adversarial Networks ◽  
Generative Adversarial Network ◽  
Fine Grained ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Cascade Structure ◽  
High Resolution Images

In this paper, we propose an Attentional Concatenation Generative Adversarial Network (ACGAN) aiming at generating 1024 × 1024 high-resolution images. First, we propose a multilevel cascade structure, for text-to-image synthesis. During training progress, we gradually add new layers and, at the same time, use the results and word vectors from the previous layer as inputs to the next layer to generate high-resolution images with photo-realistic details. Second, the deep attentional multimodal similarity model is introduced into the network, and we match word vectors with images in a common semantic space to compute a fine-grained matching loss for training the generator. In this way, we can pay attention to the fine-grained information of the word level in the semantics. Finally, the measure of diversity is added to the discriminator, which enables the generator to obtain more diverse gradient directions and improve the diversity of generated samples. The experimental results show that the inception scores of the proposed model on the CUB and Oxford-102 datasets have reached 4.48 and 4.16, improved by 2.75% and 6.42% compared to Attentional Generative Adversarial Networks (AttenGAN). The ACGAN model has a better effect on text-generated images, and the resulting image is closer to the real image.

scholarly journals 3D Geological Image Synthesis From 2D Examples Using Generative Adversarial Networks

2020 ◽  
Vol 2 ◽  
Author(s):  
Guillaume Coiffier ◽  
Philippe Renard ◽  
Sylvain Lefebvre
Keyword(s):  
Image Synthesis ◽  
Generative Adversarial Networks ◽  
Adversarial Networks
Sign in / Sign up

Export Citation Format

Share Document