Adversarial Generative Models
The minimax game, mode collapse, Wasserstein critics, and what FID does and does not measure.
5concepts
62flashcards
36minutes of reading
- 01 Adversarial Losses as a Component Why GANs largely lost as standalone generative models but their loss survived inside autoencoders, vocoders and super-resolution, and what a patch discriminator adds that L2 cannot.
- 02 The GAN Minimax Game What the discriminator is actually estimating, why the theoretically clean generator loss cannot be used in practice, and what it means that training seeks an equilibrium rather than a minimum.
- 03 What FID Measures and What It Misses The Gaussian assumption inside Frechet Inception Distance, the sample-size bias that makes numbers incomparable across papers, and why precision and recall metrics exist.
- 04 Mode Collapse and Training Instability Why a GAN generator has no incentive to cover the data distribution, the difference between full and partial collapse, and what each of the standard mitigations actually changes.
- 05 Wasserstein Critics and the Lipschitz Constraint Why earth mover distance still has a gradient when JS divergence does not, how the Kantorovich duality turns it into a trainable critic, and why enforcing the Lipschitz bound is where every practical difficulty lives.