Non-Cross Diffusion for Semantic Consistency
- URL: http://arxiv.org/abs/2312.00820v2
- Date: Sun, 03 Nov 2024 08:30:04 GMT
- Title: Non-Cross Diffusion for Semantic Consistency
- Authors: Ziyang Zheng, Ruiyuan Gao, Qiang Xu,
- Abstract summary: We introduce Non-Cross Diffusion', an innovative approach in generative modeling for learning ordinary differential equation (ODE) models.
Our methodology strategically incorporates an ascending dimension of input to effectively connect points sampled from two distributions with uncrossed paths.
- Score: 12.645444338043934
- License:
- Abstract: In diffusion models, deviations from a straight generative flow are a common issue, resulting in semantic inconsistencies and suboptimal generations. To address this challenge, we introduce `Non-Cross Diffusion', an innovative approach in generative modeling for learning ordinary differential equation (ODE) models. Our methodology strategically incorporates an ascending dimension of input to effectively connect points sampled from two distributions with uncrossed paths. This design is pivotal in ensuring enhanced semantic consistency throughout the inference process, which is especially critical for applications reliant on consistent generative flows, including various distillation methods and deterministic sampling, which are fundamental in image editing and interpolation tasks. Our empirical results demonstrate the effectiveness of Non-Cross Diffusion, showing a substantial reduction in semantic inconsistencies at different inference steps and a notable enhancement in the overall performance of diffusion models.
Related papers
- Diffusing Differentiable Representations [60.72992910766525]
We introduce a novel, training-free method for sampling differentiable representations (diffreps) using pretrained diffusion models.
We identify an implicit constraint on the samples induced by the diffrep and demonstrate that addressing this constraint significantly improves the consistency and detail of the generated objects.
arXiv Detail & Related papers (2024-12-09T20:42:58Z) - Distillation of Discrete Diffusion through Dimensional Correlations [21.078500510691747]
"Mixture" models are capable of treating dimensional correlations while remaining scalable.
"Loss functions" enable the mixture models to distill such many-step conventional models into just a few steps by learning the dimensional correlations.
Our experimental results show the effectiveness of the proposed method in distilling pretrained discrete diffusion models across image and language domains.
arXiv Detail & Related papers (2024-10-11T10:53:03Z) - Efficient Text-driven Motion Generation via Latent Consistency Training [21.348658259929053]
We propose a motion latent consistency training framework (MLCT) to solve nonlinear reverse diffusion trajectories.
By combining these enhancements, we achieve stable and consistency training in non-pixel modality and latent representation spaces.
arXiv Detail & Related papers (2024-05-05T02:11:57Z) - Convergence Analysis of Discrete Diffusion Model: Exact Implementation
through Uniformization [17.535229185525353]
We introduce an algorithm leveraging the uniformization of continuous Markov chains, implementing transitions on random time points.
Our results align with state-of-the-art achievements for diffusion models in $mathbbRd$ and further underscore the advantages of discrete diffusion models in comparison to the $mathbbRd$ setting.
arXiv Detail & Related papers (2024-02-12T22:26:52Z) - Semi-Implicit Denoising Diffusion Models (SIDDMs) [50.30163684539586]
Existing models such as Denoising Diffusion Probabilistic Models (DDPM) deliver high-quality, diverse samples but are slowed by an inherently high number of iterative steps.
We introduce a novel approach that tackles the problem by matching implicit and explicit factors.
We demonstrate that our proposed method obtains comparable generative performance to diffusion-based models and vastly superior results to models with a small number of sampling steps.
arXiv Detail & Related papers (2023-06-21T18:49:22Z) - Variance-Preserving-Based Interpolation Diffusion Models for Speech
Enhancement [53.2171981279647]
We present a framework that encapsulates both the VP- and variance-exploding (VE)-based diffusion methods.
To improve performance and ease model training, we analyze the common difficulties encountered in diffusion models.
We evaluate our model against several methods using a public benchmark to showcase the effectiveness of our approach.
arXiv Detail & Related papers (2023-06-14T14:22:22Z) - A Geometric Perspective on Diffusion Models [57.27857591493788]
We inspect the ODE-based sampling of a popular variance-exploding SDE.
We establish a theoretical relationship between the optimal ODE-based sampling and the classic mean-shift (mode-seeking) algorithm.
arXiv Detail & Related papers (2023-05-31T15:33:16Z) - A Variational Perspective on Solving Inverse Problems with Diffusion
Models [101.831766524264]
Inverse tasks can be formulated as inferring a posterior distribution over data.
This is however challenging in diffusion models since the nonlinear and iterative nature of the diffusion process renders the posterior intractable.
We propose a variational approach that by design seeks to approximate the true posterior distribution.
arXiv Detail & Related papers (2023-05-07T23:00:47Z) - Reflected Diffusion Models [93.26107023470979]
We present Reflected Diffusion Models, which reverse a reflected differential equation evolving on the support of the data.
Our approach learns the score function through a generalized score matching loss and extends key components of standard diffusion models.
arXiv Detail & Related papers (2023-04-10T17:54:38Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.