Related papers: On the Guidance of Flow Matching

On the Guidance of Flow Matching

URL: http://arxiv.org/abs/2502.02150v2
Date: Tue, 22 Apr 2025 08:45:10 GMT
Title: On the Guidance of Flow Matching
Authors: Ruiqi Feng, Tailin Wu, Chenglei Yu, Wenhao Deng, Peiyan Hu,
Abstract summary: Flow matching has shown state-of-the-art performance in various generative tasks.<n>We propose the first framework of general guidance for flow matching.
Score: 5.495430412700785
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Flow matching has shown state-of-the-art performance in various generative tasks, ranging from image generation to decision-making, where guided generation is pivotal. However, the guidance of flow matching is more general than and thus substantially different from that of its predecessor, diffusion models. Therefore, the challenge in guidance for general flow matching remains largely underexplored. In this paper, we propose the first framework of general guidance for flow matching. From this framework, we derive a family of guidance techniques that can be applied to general flow matching. These include a new training-free asymptotically exact guidance, novel training losses for training-based guidance, and two classes of approximate guidance that cover classical gradient guidance methods as special cases. We theoretically investigate these different methods to give a practical guideline for choosing suitable methods in different scenarios. Experiments on synthetic datasets, image inverse problems, and offline reinforcement learning demonstrate the effectiveness of our proposed guidance methods and verify the correctness of our flow matching guidance framework. Code to reproduce the experiments can be found at https://github.com/AI4Science-WestlakeU/flow_guidance.

Related papers

Studying Classifier(-Free) Guidance From a Classifier-Centric Perspective [100.54185280153753]
We find that both classifier guidance and classifier-free guidance achieve conditional generation by pushing the denoising diffusion trajectories away from decision boundaries. We propose a generic postprocessing step built upon flow-matching to shrink the gap between the learned distribution for a pretrained denoising diffusion model and the real data distribution.
arXiv Detail & Related papers (2025-03-13T17:59:59Z)
Training Free Guided Flow Matching with Optimal Control [6.729886762762167]
We present OC-Flow, a training-free framework for guided flow matching using optimal control.<n>We show that OC-Flow achieved superior performance in experiments on text-guided image manipulation, conditional molecule generation, and all-atom peptide design.
arXiv Detail & Related papers (2024-10-23T17:53:11Z)
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)
Elucidating The Design Space of Classifier-Guided Diffusion Generation [17.704873767509557]
We show that it is possible to achieve significant performance improvements over existing guidance schemes by leveraging off-the-shelf classifiers in a training-free fashion. Our proposed approach has great potential and can be readily scaled up to text-to-image generation tasks.
arXiv Detail & Related papers (2023-10-17T14:34:58Z)
Taxonomy Adaptive Cross-Domain Adaptation in Medical Imaging via Optimization Trajectory Distillation [73.83178465971552]
The success of automated medical image analysis depends on large-scale and expert-annotated training sets. Unsupervised domain adaptation (UDA) has been raised as a promising approach to alleviate the burden of labeled data collection. We propose optimization trajectory distillation, a unified approach to address the two technical challenges from a new perspective.
arXiv Detail & Related papers (2023-07-27T08:58:05Z)
NormAUG: Normalization-guided Augmentation for Domain Generalization [60.159546669021346]
We propose a simple yet effective method called NormAUG (Normalization-guided Augmentation) for deep learning. Our method introduces diverse information at the feature level and improves the generalization of the main path. In the test stage, we leverage an ensemble strategy to combine the predictions from the auxiliary path of our model, further boosting performance.
arXiv Detail & Related papers (2023-07-25T13:35:45Z)
Learning Trajectories are Generalization Indicators [44.53518627207067]
This paper explores the connection between learning trajectories of Deep Neural Networks (DNNs) and their generalization capabilities. We present a novel perspective for analyzing generalization error by investigating the contribution of each update step to the change in generalization error. Our approach can also track changes in generalization error when adjustments are made to learning rates and label noise levels.
arXiv Detail & Related papers (2023-04-25T05:08:57Z)
Transductive Learning for Unsupervised Text Style Transfer [60.65782243927698]
Unsupervised style transfer models are mainly based on an inductive learning approach. We propose a novel transductive learning approach based on a retrieval-based context-aware style representation.
arXiv Detail & Related papers (2021-09-16T08:57:20Z)
There and Back Again: Revisiting Backpropagation Saliency Methods [87.40330595283969]
Saliency methods seek to explain the predictions of a model by producing an importance map across each input sample. A popular class of such methods is based on backpropagating a signal and analyzing the resulting gradient. We propose a single framework under which several such methods can be unified.
arXiv Detail & Related papers (2020-04-06T17:58:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.