REVIEW 5 cited by
DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Diffusion probabilistic models have been shown to generate state-of-the-art results on several competitive image synthesis benchmarks but lack a low-dimensional, interpretable latent space, and are slow at generation. On the other hand, standard Variational Autoencoders (VAEs) typically have access to a low-dimensional latent space but exhibit poor sample quality. We present DiffuseVAE, a novel generative framework that integrates VAE within a diffusion model framework, and leverage this to design novel conditional parameterizations for diffusion models. We show that the resulting model equips diffusion models with a low-dimensional VAE inferred latent code which can be used for downstream tasks like controllable synthesis. The proposed method also improves upon the speed vs quality tradeoff exhibited in standard unconditional DDPM/DDIM models (for instance, FID of 16.47 vs 34.36 using a standard DDIM on the CelebA-HQ-128 benchmark using T=10 reverse process steps) without having explicitly trained for such an objective. Furthermore, the proposed model exhibits synthesis quality comparable to state-of-the-art models on standard image synthesis benchmarks like CIFAR-10 and CelebA-64 while outperforming most existing VAE-based methods. Lastly, we show that the proposed method exhibits inherent generalization to different types of noise in the conditioning signal. For reproducibility, our source code is publicly available at https://github.com/kpandey008/DiffuseVAE.
Forward citations
Cited by 5 Pith papers
-
FairDiffuseVQVAE: Sampling-Time Fairness in Tabular Diffusion via Conditional Refinement of Vector-Quantized Latents
FairDiffuseVQVAE reaches state-of-the-art fairness on the standard tabular benchmark (DPR 0.702, EOR 0.686) by uniform protected-attribute sampling at inference, paying ~15 AUC points of utility.
-
Neural Langevin Machine: a local asymmetric learning rule can be creative
A recurrent neural network trained with a local asymmetric contrastive-divergence rule on a kinetic energy landscape can generate and denoise images.
-
Diffusion Counterfactual Generation with Semantic Abduction
Diffusion-based causal image counterfactuals with semantic abduction improve identity preservation at a small cost in intervention effectiveness, demonstrated on Morpho-MNIST, CelebA-HQ, and mammogram artifact removal.
-
Diffusion Disambiguation Models for Partial Label Learning
DDMP applies diffusion denoising to partial label learning, refining candidate labels with a pseudo-clean label matrix and a transition-aware matrix.
-
On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning
Small binary latents conditioned via cross-attention let a diffusion autoencoder generate from a uniform Bernoulli prior with fewer steps while keeping representation quality.
Discussion (0). Sign in to comment.