Improving Continuous Normalizing Flows using a Multi-Resolution Framework
Recent work has shown that Continuous Normalizing Flows (CNFs) can serve as generative models of images with exact likelihood calculation and invertible generation/density estimation. In this work we introduce a Multi-Resolution variant of such models (MRCNF). We introduce a transformation between resolutions that allows for no change in the log likelihood. We show that this approach yields comparable likelihood values for various image datasets, with improved performance at higher resolutions, with fewer parameters, using only 1 GPU.
Code (0)
등록된 구현이 없습니다.
Tasks
Density EstimationGPUMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Multi-Resolution Continuous Normalizing Flows
Recent work has shown that Neural Ordinary Differential Equations (ODEs) can serve as generative models of images using the perspective of Continuous Normalizing Flows (CNFs). Such models offer exact likelihood calculati…
Density EstimationGPUImage GenerationEAGLE: Contextual Point Cloud Generation via Adaptive Continuous Normalizing Flow with Self-Attention
As 3D point clouds become the prevailing shape representation in computer vision, how to generate high-resolution point clouds has become a pressing issue. Flow-based generative models can effectively perform point cloud…
Point Cloud GenerationLearning normalizing flows from Entropy-Kantorovich potentials
We approach the problem of learning continuous normalizing flows from a dual perspective motivated by entropy-regularized optimal transport, in which continuous normalizing flows are cast as gradients of scalar potential…
Learning Likelihoods with Conditional Normalizing Flows
Normalizing Flows (NFs) are able to model complicated distributions p(y) with strong inter-dimensional correlations and high multimodality by transforming a simple base density p(z) through an invertible neural network u…
Structured PredictionSuper-ResolutionMulti-Scale Continuous Normalizing Flows
We introduce a multi-scale variant of Continuous Normalizing Flows, and explore the computation of likelihood values. We also introduce a Wavelet-version of the model. However, we find that this formulation is flawed in …