| Description |
1 online resource (1 volume) |
|
text rdacontent |
|
computer c rdamedia |
|
online resource cr rdacarrier |
| Note |
Includes index. |
| Summary |
"Generative Adversarial Networks (GAN) have started a revolution in Deep Learning, and today GAN is one of the most researched topics in Artificial Intelligence. Generative Adversarial Networks for Image-to-Image Translation provides a comprehensive overview of the GAN (Generative Adversarial Network) concept starting from the original GAN network to various GAN-based systems such as Deep Convolutional GANs (DCGANs), Conditional GANs (cGANs), StackGAN, Wasserstein GANs (WGAN), cyclical GANs, and many more. The book also provides readers with detailed real-world applications and common projects built using the GAN system with respective Python code. A typical GAN system consists of two neural networks, i.e., generator and discriminator. Both of these networks contest with each other, similar to game theory. The generator is responsible for generating quality images that should resemble ground truth, and the discriminator is accountable for identifying whether the generated image is a real image or a fake image generated by the generator. Being one of the unsupervised learning-based architectures, GAN is a preferred method in cases where labeled data is not available. GAN can generate high-quality images, images of human faces developed from several sketches, convert images from one domain to another, enhance images, combine an image with the style of another image, change the appearance of a human face image to show the effects in the progression of aging, generate images from text, and many more applications. GAN is helpful in generating output very close to the output generated by humans in a fraction of second, and it can efficiently produce high-quality music, speech, and images"-- Provided by publisher. |
| Contents |
Front Cover -- Generative Adversarial Networks for Image-to-Image Translation -- Copyright -- Contents -- Contributors -- Chapter 1: Super-resolution-based GAN for image processing: Recent advances and future trends -- 1.1. Introduction -- 1.1.1. Train the discriminator -- 1.1.2. Train the generator -- 1.1.3. Organization of the chapter -- 1.2. Background study -- 1.3. SR-GAN model for image processing -- 1.3.1. Architecture of SR-GAN -- 1.3.2. Network architecture -- 1.3.3. Perceptual loss -- 1.3.3.1. Content loss -- 1.3.3.2. Adversarial loss -- 1.4. Case study |
|
1.4.1. Case study 1: Application of EE-GAN to enhance object detection -- 1.4.2. Case study 2: Edge-enhanced GAN for remote sensing image -- 1.4.3. Case study 3: Application of SRGAN on video surveillance and forensic application -- 1.4.4. Case study 4: Super-resolution of video using SRGAN -- 1.5. Open issues and challenges -- 1.6. Conclusion and future scope -- References -- Chapter 2: GAN models in natural language processing and image translation -- 2.1. Introduction -- 2.1.1. Variational auto encoders -- 2.1.1.1. Drawback of VAE -- 2.1.2. Brief introduction to GAN |
|
2.2. Basic GAN model classification based on learning -- 2.2.1. Unsupervised learning -- 2.2.1.1. Vanilla GAN -- 2.2.1.2. WGAN -- 2.2.1.3. WGAN-GP -- 2.2.1.4. Info GAN -- 2.2.1.5. BEGAN -- 2.2.1.6. Unsupervised sequential GAN -- 2.2.1.7. Parallel GAN -- 2.2.1.8. Cycle GAN -- 2.2.2. Semisupervised learning -- 2.2.2.1. Semi GAN -- 2.2.3. Supervised learning -- 2.2.3.1. CGAN -- 2.2.3.2. BiGAN -- 2.2.3.3. ACGAN -- 2.2.3.4. Supervised seq-GAN -- 2.2.4. Comparison of GAN models -- 2.2.5. Pros and cons of the GAN models -- 2.3. GANs in natural language processing |
|
2.3.1. Application of GANs in natural language processing -- 2.3.1.1. Generation of semantically similar human-understandable summaries using SeqGAN with policy gradient -- Semantic similarity discriminator -- 2.3.1.2. Generation of quality language descriptions and ranking using RankGAN -- 2.3.1.3. Dialogue generation using reinforce GAN -- 2.3.1.4. Text style transfer using UGAN -- 2.3.1.5. Tibetan question-answer corpus generation using Qu-GAN -- 2.3.1.6. Generation of the sentence with lexical constraints using BFGAN -- 2.3.1.7. Short-spoken language intent classification with cSeq-GAN |
|
2.3.1.8. Recognition of Chinese characters using TH-GAN -- 2.3.2. NLP datasets -- 2.4. GANs in image generation and translation -- 2.4.1. Applications of GANs in image generation and translation -- 2.4.1.1. Ensemble learning GANs in face forensics -- 2.4.1.2. Spherical image generation from the 2D sketch using SGANs -- 2.4.1.3. Generation of radar images using TsGAN -- 2.4.1.4. Generation of CT from MRI using MCRCGAN -- 2.4.1.5. Generation of scenes from text using text-to-image GAN -- 2.4.1.6. Gastritis image generation using PG-GAN -- 2.4.1.7. Image-to-image translation using quality-aware GAN |
| Subject |
Machine learning.
|
|
Artificial intelligence.
|
|
Neural networks (Computer science)
|
|
Generative programming (Computer science)
|
|
Apprentissage automatique.
|
|
Intelligence artificielle.
|
|
Réseaux neuronaux (Informatique)
|
|
Programmation générative.
|
|
artificial intelligence.
|
|
Artificial intelligence
|
|
Generative programming (Computer science)
|
|
Machine learning
|
|
Neural networks (Computer science)
|
| Added Author |
Solanki, Arun, 1985- editor.
|
|
Nayyar, Anand, editor.
|
|
Naved, Mohd, editor.
|
| Other Form: |
Print version: 0128235195 |
| ISBN |
0128236132 (ePub ebook) |
|
9780128236130 (electronic bk.) |
|
0128235195 |
|
9780128235195 |
| Standard No. |
AU@ 000069461248 |
|
AU@ 000069620629 |
|
AU@ 000069692535 |
|
