Denoising Diffusion Generative Models Secretly Calculate Attentions

2026-09-01

AI Summary

研究揭示了去噪扩散模型隐含使用类似Transformer的注意力机制，提出基于此简化图像生成算法，减少训练时间和计算资源。

Abstract

Denoising diffusion models are the dominant architecture for image generation, whereas most natural language generation and modeling are primarily handled by well-known transformer architectures employing attention mechanism. Here, we show that diffusion models also inherently use an attention mechanism very similar to that of transformers. Therefore, attention emerges as a universal machine learning principle, based on a general training objective. We also show similarities in basic functional principle of auto-encoders and attention-based models. These equivalences allows us to interchange these designs based on practical requirements. As an example, we can reformulate the diffusion framework to reduce the lengthy training process and computation-intensive image generation. Using this approach, a simplified algorithm is proposed for image generation which is based on attention mechanism. Results show that the attention-based implementation achieves comparable performance with significantly less effort and computational resources.

Problem

• Denoising Diffusion Models
• Attention Mechanism
• Image Generation

Innovation

• attention mechanism
• denoising diffusion models
• transformers
• image generation
• computation reduction