Self-Attention in Denoising Diffusion Models

Home

Discover

Bookmarks

Keep Up With Latest Trending Papers. Computer Science, AI and Machine Learning and more.Subscribe

Artificial Intelligence

Self-Attention in Denoising Diffusion Models

Improving Sample Quality of Diffusion Models Using Self-Attention Guidance

Denoising diffusion models (ddms) have been actively researched and attracted strong attention due to their capability to generate images with high quality and diversity.

However, the internal self-attention mechanism working inside the denoising diffusion models is under-explored.

Next, we verify the hypotheses about the self-attention map by conducting frequency analysisand testing the relationships with the generated objects.

In consequence, we find out that the attention map is closely related to the quality of generated images and can guide existing pretrained diffusionmodels to generate images with higher fidelity.

In addition to the enhanced sample quality when used alone, we show that the results are further improved by combining our method with classifier guidance on imagenet 128x128.