系统梳理扩散模型中注意力机制的设计与应用，揭示其核心作用
Attention in Diffusion Model: A Survey
- 按结构组件分类注意力改进方法，构建统一分析框架
- 总结注意力在多模态任务中的性能提升效果
- 指出当前研究空白，为后续方向提供参考
注意力机制已成为扩散模型的核心组成部分，显著提升了其在生成与判别任务中的表现。本文系统综述了注意力在扩散模型中的角色、设计模式与操作方式，覆盖不同模态与任务。提出一个统一的分类体系，根据影响的结构组件对注意力相关修改进行划分，为理解其功能多样性提供清晰视角。除回顾架构创新外，还分析了注意力在各类应用中的性能增益。同时指出现有局限与未充分探索领域，并展望未来研究方向。本研究为理解扩散模型的发展脉络提供了重要洞见，尤其关注注意力的集成化与普适性作用。
原文摘要 · Abstract (English)
Attention mechanisms have become a foundational component in diffusion models, significantly influencing their capacity across a wide range of generative and discriminative tasks. This paper presents a comprehensive survey of attention within diffusion models, systematically analysing its roles, design patterns, and operations across different modalities and tasks. We propose a unified taxonomy that categorises attention-related modifications into parts according to the structural components they affect, offering a clear lens through which to understand their functional diversity. In addition to reviewing architectural innovations, we examine how attention mechanisms contribute to performance improvements in diverse applications. We also identify current limitations and underexplored areas, and outline potential directions for future research. Our study provides valuable insights into the evolving landscape of diffusion models, with a particular focus on the integrative and ubiquitous role of attention.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。