Related Computer Vision Links
Learn Gan Computer Vision Tutorial, validate concepts with Gan Computer Vision MCQ Questions, and prepare interviews through Gan Computer Vision Interview Questions and Answers.
GANs Introduction MCQ
Two networks play a game: one fakes data, the other judges—together they can synthesize realistic images.
Generator
z → image
Discriminator
Real vs fake
Min–max
Adversarial
Stability
Mode collapse
Generative adversarial networks
GANs train a generator G(z) to fool a discriminator D(x) that classifies real vs fake. The minimax objective leads to Nash equilibrium where samples match the data distribution at optimality (idealized). Practice requires balancing learning rates, architectures, and regularizers; mode collapse remains a classic failure mode.
The two-player game
D maximizes correct classification; G minimizes log(1−D(G(z))) or related objectives so fakes look real.
Key ideas
Generator
Maps noise z to samples in data space.
Discriminator
Scores real data high and fakes low.
Non-saturating G loss
Common reformulation so G gets stronger gradients early.
Mode collapse
G outputs limited variety; detectors see repeated patterns.
Training loop
Sample z → G(z) → update D on real/fake → update G to fool D