- Keywords: Energy-based model, generative model, image translation, Langevin dynamics
- Abstract: Energy-based models (EBMs) parameterized by neural networks can be trained by the Markov chain Monte Carlo (MCMC) sampling-based maximum likelihood estimation. Despite the recent significant success of EBMs in image generation, the current approaches to train EBMs are unstable and have difficulty synthesizing diverse and high-fidelity images. In this paper, we propose to train EBMs via a multistage coarse-to-fine expanding and sampling strategy, which starts with learning a coarse-level EBM from images at low resolution and then gradually transits to learn a finer-level EBM from images at higher resolution by expanding the energy function as the learning progresses. The proposed framework is computationally efficient with smooth learning and sampling. It achieves the best performance on image generation amongst all EBMs and is the first successful EBM to synthesize high-fidelity images at $512\times512$ resolution. It can also be useful for image restoration and out-of-distribution detection. Lastly, the proposed framework is further generalized to the one-sided unsupervised image-to-image translation and beats baseline methods in terms of model size and training budget. We also present a gradient-based generative saliency method to interpret the translation dynamics.
- One-sentence Summary: We propose a coarse-to-fine expanding and sampling strategy for training energy-based models.
- Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
- Supplementary Material: zip