GAN for image generation in Computer Vision - Cheat Sheet & Quick Revision

Recall & Review

beginner

What does GAN stand for in machine learning?

GAN stands for Generative Adversarial Network. It is a type of model used to generate new data similar to a given dataset.

beginner

What are the two main parts of a GAN?

A GAN has two parts: the Generator, which creates fake images, and the Discriminator, which tries to tell real images from fake ones.

intermediate

How does the Generator learn to create better images?

The Generator learns by trying to fool the Discriminator. When the Discriminator is tricked, the Generator improves its image creation.

beginner

What is the role of the Discriminator in a GAN?

The Discriminator's role is to classify images as real (from the dataset) or fake (from the Generator). It helps the Generator improve by providing feedback.

intermediate

Why is GAN training considered a game between two networks?

GAN training is like a game because the Generator and Discriminator compete: the Generator tries to create realistic images, and the Discriminator tries to detect fakes. This competition improves both.

What is the main goal of the Generator in a GAN?

A To label images in the dataset

B To classify images as real or fake

C To create images that look real enough to fool the Discriminator

D To reduce the size of the dataset

The Generator tries to create images that look real to trick the Discriminator.

Which part of a GAN decides if an image is real or fake?

A Generator

B Discriminator

C Encoder

D Decoder

The Discriminator's job is to tell if an image is real or generated (fake).

During GAN training, what happens when the Discriminator gets better at spotting fakes?

A The training ends immediately

B The Generator stops learning

C The Discriminator becomes the Generator

D The Generator improves to create more realistic images

As the Discriminator improves, the Generator must create better images to fool it.

What kind of data is typically generated by GANs in image generation tasks?

A New images similar to training images

B Audio signals

C Text descriptions

D Random noise

GANs generate new images that look like the images they were trained on.

Why is GAN training described as adversarial?

A Because the Generator and Discriminator compete against each other

B Because it uses adversarial examples for testing

C Because it trains on adversarial attacks

D Because it uses adversarial loss only for the Discriminator

The Generator and Discriminator compete, which is why the training is called adversarial.

Explain how the Generator and Discriminator work together during GAN training for image generation.

Think of it as a game where one tries to trick the other.

Describe why GANs are useful for generating new images and how their training process helps improve image quality.

Focus on the role of competition and learning from feedback.