Timezone: »
Score-based generative models (SGMs) have recently demonstrated impressive results in terms of both sample quality and distribution coverage. However, they are usually applied directly in data space and often require thousands of network evaluations for sampling. Here, we propose the Latent Score-based Generative Model (LSGM), a novel approach that trains SGMs in a latent space, relying on the variational autoencoder framework. Moving from data to latent space allows us to train more expressive generative models, apply SGMs to non-continuous data, and learn smoother SGMs in a smaller space, resulting in fewer network evaluations and faster sampling. To enable training LSGMs end-to-end in a scalable and stable manner, we (i) introduce a new score-matching objective suitable to the LSGM setting, (ii) propose a novel parameterization of the score function that allows SGM to focus on the mismatch of the target distribution with respect to a simple Normal one, and (iii) analytically derive multiple techniques for variance reduction of the training objective. LSGM obtains a state-of-the-art FID score of 2.10 on CIFAR-10, outperforming all existing generative results on this dataset. On CelebA-HQ-256, LSGM is on a par with previous SGMs in sample quality while outperforming them in sampling time by two orders of magnitude. In modeling binary images, LSGM achieves state-of-the-art likelihood on the binarized OMNIGLOT dataset.
Author Information
Arash Vahdat (NVIDIA Research)
Karsten Kreis (NVIDIA)
Jan Kautz (NVIDIA)
More from the Same Authors
-
2020 : Differentially Private Generative Models Through Optimal Transport »
Karsten Kreis -
2021 : Physics Informed RNN-DCT Networks for Time-Dependent Partial Differential Equations »
Benjamin Wu · Oliver Hennigh · Jan Kautz · Sanjay Choudhry · Wonmin Byeon -
2022 : Latent Space Diffusion Models of Cryo-EM Structures »
Karsten Kreis · Tim Dockhorn · Zihao Li · Ellen Zhong -
2023 Poster: Generalizable One-shot Neural Head Avatar »
Xueting Li · Shalini De Mello · Sifei Liu · Koki Nagano · Umar Iqbal · Jan Kautz -
2023 Poster: Convolutional State Space Models for Long-Range Spatiotemporal Modeling »
Jimmy Smith · Shalini De Mello · Jan Kautz · Scott Linderman · Wonmin Byeon -
2023 Tutorial: Latent Diffusion Models: Is the Generative AI Revolution Happening in Latent Space? »
· Arash Vahdat · Karsten Kreis -
2022 : Latent Space Diffusion Models of Cryo-EM Structures »
Karsten Kreis · Tim Dockhorn · Zihao Li · Ellen Zhong -
2022 : Invited talk: Karsten Kreis »
Karsten Kreis -
2021 Poster: A Contrastive Learning Approach for Training Variational Autoencoder Priors »
Jyoti Aneja · Alex Schwing · Jan Kautz · Arash Vahdat -
2021 Poster: EditGAN: High-Precision Semantic Image Editing »
Huan Ling · Karsten Kreis · Daiqing Li · Seung Wook Kim · Antonio Torralba · Sanja Fidler -
2021 Poster: Controllable and Compositional Generation with Latent-Space Energy-Based Models »
Weili Nie · Arash Vahdat · Anima Anandkumar -
2021 Poster: ATISS: Autoregressive Transformers for Indoor Scene Synthesis »
Despoina Paschalidou · Amlan Kar · Maria Shugrina · Karsten Kreis · Andreas Geiger · Sanja Fidler -
2021 Poster: Don’t Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence »
Tianshi Cao · Alex Bie · Arash Vahdat · Sanja Fidler · Karsten Kreis -
2021 Poster: Coupled Segmentation and Edge Learning via Dynamic Graph Propagation »
Zhiding Yu · Rui Huang · Wonmin Byeon · Sifei Liu · Guilin Liu · Thomas Breuel · Anima Anandkumar · Jan Kautz -
2020 Poster: NVAE: A Deep Hierarchical Variational Autoencoder »
Arash Vahdat · Jan Kautz -
2020 Poster: Variational Amodal Object Completion »
Huan Ling · David Acuna · Karsten Kreis · Seung Wook Kim · Sanja Fidler -
2020 Spotlight: NVAE: A Deep Hierarchical Variational Autoencoder »
Arash Vahdat · Jan Kautz -
2020 Poster: Online Adaptation for Consistent Mesh Reconstruction in the Wild »
Xueting Li · Sifei Liu · Shalini De Mello · Kihwan Kim · Xiaolong Wang · Ming-Hsuan Yang · Jan Kautz -
2020 Poster: Convolutional Tensor-Train LSTM for Spatio-Temporal Learning »
Jiahao Su · Wonmin Byeon · Jean Kossaifi · Furong Huang · Jan Kautz · Anima Anandkumar -
2019 Poster: Few-shot Video-to-Video Synthesis »
Ting-Chun Wang · Ming-Yu Liu · Andrew Tao · Guilin Liu · Bryan Catanzaro · Jan Kautz -
2019 Poster: Joint-task Self-supervised Learning for Temporal Correspondence »
Xueting Li · Sifei Liu · Shalini De Mello · Xiaolong Wang · Jan Kautz · Ming-Hsuan Yang -
2019 Poster: Dancing to Music »
Hsin-Ying Lee · Xiaodong Yang · Ming-Yu Liu · Ting-Chun Wang · Yu-Ding Lu · Ming-Hsuan Yang · Jan Kautz -
2018 : Jan Kautz »
Jan Kautz -
2018 Poster: Context-aware Synthesis and Placement of Object Instances »
Donghoon Lee · Sifei Liu · Jinwei Gu · Ming-Yu Liu · Ming-Hsuan Yang · Jan Kautz -
2018 Poster: Video-to-Video Synthesis »
Ting-Chun Wang · Ming-Yu Liu · Jun-Yan Zhu · Guilin Liu · Andrew Tao · Jan Kautz · Bryan Catanzaro -
2017 : Poster Session (encompasses coffee break) »
Beidi Chen · Borja Balle · Daniel Lee · iuri frosio · Jitendra Malik · Jan Kautz · Ke Li · Masashi Sugiyama · Miguel A. Carreira-Perpinan · Ramin Raziperchikolaei · Theja Tulabandhula · Yung-Kyun Noh · Adams Wei Yu -
2017 Poster: Unsupervised Image-to-Image Translation Networks »
Ming-Yu Liu · Thomas Breuel · Jan Kautz -
2017 Spotlight: Unsupervised Image-to-Image Translation Networks »
Ming-Yu Liu · Thomas Breuel · Jan Kautz -
2017 Poster: Learning Affinity via Spatial Propagation Networks »
Sifei Liu · Shalini De Mello · Jinwei Gu · Guangyu Zhong · Ming-Hsuan Yang · Jan Kautz -
2017 Poster: Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks »
Arash Vahdat