Highlights: In the previous post, we built a Deep Convolutional Generative Adversarial Network (DCGAN) for the MNIST Handwritten Digit Dataset. Taking forward the encouraging results we displayed in the previous chapter, let us build our first DCGAN model using the standard small image dataset, CIFAR-10. By using a small and already well-understood dataset such as CIFAR-10, we can speed up the development and training of our model so that we are can focus more on…
Read more

Highlights: In the previous posts, we brushed the surface of our book’s hero concept of Generative Adversarial Networks (GANs). We also learned about training stable GANs using Deep Convolutional Generative Adversarial Networks (DCGANs). In this post, we will dive a little bit more into the details of the GANs. We will observe their mathematical foundations through the fundamentals of probability and optimization methods. So, let’s begin. Tutorial overview: Adversarial Learning The Adversarial Game Loss Function…
Read more

Highlights: There has been significant progress, in the past few years, when it comes to developing techniques and algorithms for reconstructing, tracking, and analyzing human faces. The Computer Vision communities across the globe are working hard to improve the speed, accuracy, and user-friendliness of these models. As a result, many impressive case studies have presented amazing results in the most challenging problems. Today, through this blog post, we’ll try to learn about the reconstruction and…
Read more

Highlights: What is real, really? The ‘Deepfake’ technology has made advances into the mainstream and made it difficult to prove the authenticity of videos and faces. Even though the technology itself isn’t all that bad, its unethical use has victimized many across the globe. In this blog post, we will learn about the underlying algorithms of these so-called Deepfakes, based on Generative Adversarial Networks (GANs). We will also explore the creation and detection of Deepfakes…
Read more

Highlights: The evolution of Generative Adversarial Networks (GANs) has brought about a change in how researchers solve certain Computer Vision problems such as conditional image generation, 3D object generation, video synthesis, and more. In this tutorial blog post, we will go into detail about the fundamentals of generative learning, its categories, and the different types of GANs that are popular in the Computer Vision field of research. So let’s begin! Tutorial Overview: Generative Learning Vanilla GAN…
Read more