Representation Learning in Diffusion and Flow-based Model: An Application Aspect

2026-08-25

AI Summary

本文探讨了扩散模型和流模型在表示学习中的应用，提出一个三层框架来组织现有工作，并分类方法以解决图像分类等任务中的挑战。

Abstract

Diffusion models and flow-based models have recently become the dominant paradigms in generative modeling, largely due to their ability to learn rich, multi-level visual representations through large-scale training. This creates a bidirectional relationship between generative models and representation learning: improving representation learning enhances generation quality, while the learned representations can be leveraged for broader understanding tasks. This survey systematically explores this interplay with a focus on applications. We propose a three-tier progressive framework that organizes existing works from three perspectives: using representation learning to improve generative capabilities, exploiting generative models to extract representations for perception tasks, and ultimately moving toward general-purpose unified applications. We systematically categorize representative methods across a wide range of downstream tasks, including image classification, dense visual prediction, instance-level perception, and annotation-scarce scenarios. By providing a unified taxonomy and identifying key challenges, this survey aims to clarify the underlying logic of current research and suggest promising directions for future exploration. We hope this work can serve as a valuable reference for researchers interested in harnessing the representation power of generative models for applications beyond generation.

Problem

• Representation Learning
• Diffusion Models
• Flow-based Models
• Generative Modeling
• Applications

Innovation

• representation learning
• generative models
• three-tier progressive framework
• downstream tasks