M-EBM: Towards Understanding the Manifolds of Energy-Based Models
Energy-based models (EBMs) exhibit a variety of desirable properties in predictive tasks, such as generality, simplicity and compositionality. However, training EBMs on high-dimensional datasets remains unstable and expensive. In this paper, we present a Manifold EBM (M-EBM) to boost the overall performance of unconditional EBM and Joint Energy-based Model (JEM). Despite its simplicity, M-EBM significantly improves unconditional EBMs in training stability and speed on a host of benchmark datasets, such as CIFAR10, CIFAR100, CelebA-HQ, and ImageNet 32x32. Once class labels are available, label-incorporated M-EBM (M-JEM) further surpasses M-EBM in image generation quality with an over 40% FID improvement, while enjoying improved accuracy. The code can be found at https://github.com/sndnyang/mebm.
Code (1)
Tasks
Image GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
SDDM: Score-Decomposed Diffusion Models on Manifolds for Unpaired Image-to-Image Translation
Recent score-based diffusion models (SBDMs) show promising results in unpaired image-to-image translation (I2I). However, existing methods, either energy-based or statistically-based, provide no explicit form of the inte…
DenoisingImage DenoisingImage GenerationImage-to-Image TranslationConvergence of graph Dirichlet energies and graph Laplacians on intersecting manifolds of varying dimensions
We study $Γ$-convergence of graph Dirichlet energies and spectral convergence of graph Laplacians on unions of intersecting manifolds of potentially different dimensions. Our investigation is motivated by problems of mac…
Uncertainty quantification of receptor ligand binding sites prediction
Recent advancements in protein docking site prediction have highlighted the limitations of traditional rigid docking algorithms, like PIPER, which often neglect critical stochastic elements such as solvent-induced fluctu…
PredictionUncertainty QuantificationSpiking Graph Neural Network on Riemannian Manifolds
Graph neural networks (GNNs) have become the dominant solution for learning on graphs, the typical non-Euclidean structures. Conventional GNNs, constructed with the Artificial Neuron Network (ANN), have achieved impressi…
Graph Neural NetworkLearning Solution Manifolds for Control Problems via Energy Minimization
A variety of control tasks such as inverse kinematics (IK), trajectory optimization (TO), and model predictive control (MPC) are commonly formulated as energy minimization problems. Numerical solutions to such problems a…
Imitation LearningModel Predictive Control