D-Flow: Differentiating through Flows for Controlled Generation

• URL: http://arxiv.org/abs/2402.14017v2
• Date: Sun, 21 Jul 2024 11:19:38 GMT
• Title: D-Flow: Differentiating through Flows for Controlled Generation
• Authors: Heli Ben-Hamu, Omri Puny, Itai Gat, Brian Karrer, Uriel Singer, Yaron Lipman,
• Abstract summary: We introduce D-Flow, a framework for controlling the generation process by differentiating through the flow. We motivate this framework by our key observation stating that for Diffusion/FM models trained with Gaussian probability paths, differentiating through the generation process projects gradient on the data manifold. We validate our framework on linear and non-linear controlled generation problems including: image and audio inverse problems and conditional molecule generation reaching state of the art performance across all.
• Score: 37.80603174399585
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Taming the generation outcome of state of the art Diffusion and Flow-Matching (FM) models without having to re-train a task-specific model unlocks a powerful tool for solving inverse problems, conditional generation, and controlled generation in general. In this work we introduce D-Flow, a simple framework for controlling the generation process by differentiating through the flow, optimizing for the source (noise) point. We motivate this framework by our key observation stating that for Diffusion/FM models trained with Gaussian probability paths, differentiating through the generation process projects gradient on the data manifold, implicitly injecting the prior into the optimization process. We validate our framework on linear and non-linear controlled generation problems including: image and audio inverse problems and conditional molecule generation reaching state of the art performance across all.

Related papers

• Local Flow Matching Generative Models [19.859984725284896]
  Flow Matching (FM) is a simulation-free method for learning a continuous and invertible flow to interpolate between two distributions. We introduce Local Flow Matching (LFM), which learns a sequence of FM sub-models and each matches a diffusion process up to the time of the step size in the data-to-noise direction. In experiments, we demonstrate the improved training efficiency and competitive generative performance of LFM compared to FM.
  arXiv  Detail & Related papers  (2024-10-03T14:53:10Z)
• Text-to-Image Rectified Flow as Plug-and-Play Priors [52.586838532560755]
  Rectified flow is a novel class of generative models that enforces a linear progression from the source to the target distribution. We show that rectified flow approaches surpass in terms of generation quality and efficiency, requiring fewer inference steps. Our method also displays competitive performance in image inversion and editing.
  arXiv  Detail & Related papers  (2024-06-05T14:02:31Z)
• Guided Flows for Generative Modeling and Decision Making [55.42634941614435]
  We show that Guided Flows significantly improves the sample quality in conditional image generation and zero-shot text synthesis-to-speech. Notably, we are first to apply flow models for plan generation in the offline reinforcement learning setting ax speedup in compared to diffusion models.
  arXiv  Detail & Related papers  (2023-11-22T15:07:59Z)
• Free-form Flows: Make Any Architecture a Normalizing Flow [8.163244519983298]
  We develop a training procedure that uses an efficient estimator for the gradient of the change of variables formula. This enables any dimension-preserving neural network to serve as a generative model through maximum likelihood training. We achieve excellent results in molecule generation benchmarks utilizing $E(n)$-equivariant networks.
  arXiv  Detail & Related papers  (2023-10-25T13:23:08Z)
• Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization [87.21285093582446]
  Diffusion Generative Flow Samplers (DGFS) is a sampling-based framework where the learning process can be tractably broken down into short partial trajectory segments. Our method takes inspiration from the theory developed for generative flow networks (GFlowNets)
  arXiv  Detail & Related papers  (2023-10-04T09:39:05Z)
• Training-free Linear Image Inverses via Flows [17.291903204982326]
  We propose a training-free method for solving linear inverse problems by using pretrained flow models. Our approach requires no problem-specific tuning across an extensive suite of noisy linear inverse problems on high-dimensional datasets.
  arXiv  Detail & Related papers  (2023-09-25T22:13:16Z)
• Generative Flows with Invertible Attentions [135.23766216657745]
  We introduce two types of invertible attention mechanisms for generative flow models. We exploit split-based attention mechanisms to learn the attention weights and input representations on every two splits of flow feature maps. Our method provides invertible attention modules with tractable Jacobian determinants, enabling seamless integration of it at any positions of the flow-based models.
  arXiv  Detail & Related papers  (2021-06-07T20:43:04Z)
• Refining Deep Generative Models via Discriminator Gradient Flow [18.406499703293566]
  Discriminator Gradient flow (DGflow) is a new technique that improves generated samples via the gradient flow of entropy-regularized f-divergences. We show that DGflow leads to significant improvement in the quality of generated samples for a variety of generative models.
  arXiv  Detail & Related papers  (2020-12-01T19:10:15Z)
• Normalizing Flows with Multi-Scale Autoregressive Priors [131.895570212956]
  We introduce channel-wise dependencies in their latent space through multi-scale autoregressive priors (mAR) Our mAR prior for models with split coupling flow layers (mAR-SCF) can better capture dependencies in complex multimodal data. We show that mAR-SCF allows for improved image generation quality, with gains in FID and Inception scores compared to state-of-the-art flow-based models.
  arXiv  Detail & Related papers  (2020-04-08T09:07:11Z)

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.