Latent Geometry and Memorization in Generative Models
It can be difficult to tell whether a trained generative model has learned to generate novel examples or has simply memorized a specific set of outputs. In published work, it is common to attempt to address this visually, for example by displaying a generated example and its nearest neighbor(s) in the training set (in, for example, the L2 metric). As any generative model induces a probability density on its output domain, we propose studying this density directly. We first study the geometry of the latent representation and generator, relate this to the output density, and then develop techniques to compute and inspect the output density. As an application, we demonstrate that "memorization" tends to a density made of delta functions concentrated on the memorized examples. We note that without first understanding the geometry, the measurement would be essentially impossible to make.
Code (0)
등록된 구현이 없습니다.
Tasks
MemorizationSimilar Papers 제목 키워드 기반
Latent Diffusion Inversion Requires Understanding the Latent Space
The recovery of training data from generative models ("model inversion") has been extensively studied for diffusion models in the data domain as a memorization/overfitting phenomenon. Latent diffusion models (LDMs), whic…
Understanding the Local Geometry of Generative Model Manifolds
Deep generative models learn continuous representations of complex data manifolds using a finite number of samples during training. For a pre-trained generative model, the common way to evaluate the quality of the manifo…
MemorizationmodelUnconditional Latent Diffusion Models Memorize Patient Imaging Data: Implications for Openly Sharing Synthetic Data
AI models present a wide range of applications in the field of medicine. However, achieving optimal performance requires access to extensive healthcare data, which is often not readily available. Furthermore, the imperat…
Copy DetectionData AugmentationImage GenerationMemorization+1Investigating Data Memorization in 3D Latent Diffusion Models for Medical Image Synthesis
Generative latent diffusion models have been established as state-of-the-art in data generation. One promising application is generation of realistic synthetic medical imaging data for open data sharing without compromis…
Contrastive LearningImage GenerationMemorizationMemorization in 3D Shape Generation: An Empirical Study
Generative models are increasingly used in 3D vision to synthesize novel shapes, yet it remains unclear whether their generation relies on memorizing training shapes. Understanding their memorization could help prevent t…