Learning disconnected manifolds: a no GAN's land
Typical architectures of Generative Adversarial Networks make use of a unimodal latent/input distribution transformed by a continuous generator. Consequently, the modeled distribution always has connected support which is cumbersome when learning a disconnected set of manifolds. We formalize this problem by establishing a "no free lunch" theorem for the disconnected manifold learning stating an upper-bound on the precision of the targeted distribution. This is done by building on the necessary existence of a low-quality region where the generator continuously samples data between two disconnected modes. Finally, we derive a rejection sampling method based on the norm of generator’s Jacobian and show its efficiency on several generators including BigGAN.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Learning disconnected manifolds: a no GANs land
Typical architectures of Generative AdversarialNetworks make use of a unimodal latent distribution transformed by a continuous generator. Consequently, the modeled distribution always has connected support which is cumbe…
Learning Disconnected Manifolds: Avoiding The No Gan's Land by Latent Rejection
Standard formulations of GANs, where a continuous function deforms a connected latent space, have been shown to be misspecified when fitting disconnected manifolds. In particular, when covering different classes of image…
DiRe-RAPIDS: Topology-faithful dimensionality reduction at scale
Dimensionality reduction methods such as UMAP and t-SNE are central tools for visualising high-dimensional data, but their local-neighborhood objectives can preserve sampling noise while distorting global topology. We sh…
Dimensionality ReductionDisconnected Manifold Learning for Generative Adversarial Networks
Natural images may lie on a union of disjoint manifolds rather than one globally connected manifold, and this can cause several difficulties for the training of common Generative Adversarial Networks (GANs). In this work…
Flexible Multi-Generator Model with Fused Spatiotemporal Graph for Trajectory Prediction
Trajectory prediction plays a vital role in automotive radar systems, facilitating precise tracking and decision-making in autonomous driving. Generative adversarial networks with the ability to learn a distribution over…
Autonomous DrivingDecision MakingTrajectory Prediction