paper-with-me

Papers

GradCheck: Analyzing classifier guidance gradients for conditional diffusion sampling

2024-06-25 · Philipp Vaeth, Alexander M. Fruehwald, Benjamin Paassen, Magda Gregorova

To sample from an unconditionally trained Denoising Diffusion Probabilistic Model (DDPM), classifier guidance adds conditional information during sampling, but the gradients from classifiers, especially those not trained on noisy images, are often unstable. This study conducts a gradient analysis comparing robust and non-robust classifiers, as well as multiple gradient stabilization techniques. Experimental results demonstrate that these techniques significantly improve the quality of class-conditional samples for non-robust classifiers by providing more stable and informative classifier guidance gradients. The findings highlight the importance of gradient stability in enhancing the performance of classifier guidance, especially on non-robust classifiers.

📄 PDF Abstract BibTeX arXiv:2406.17399

Code (0)

등록된 구현이 없습니다.

Tasks

Denoising

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Rethinking Conditional Diffusion Sampling with Progressive Guidance

2023-09-21 · NeurIPS 2023 11

This paper tackles two critical challenges encountered in classifier guidance for diffusion generative models, i.e., the lack of diversity and the presence of adversarial effects. These issues often result in a scarcity …

Enhancing Diffusion-Based Image Synthesis with Robust Classifier Guidance

2022-08-18 · Bahjat Kawar, Roy Ganz, Michael Elad

Denoising diffusion probabilistic models (DDPMs) are a recent family of generative models that achieve state-of-the-art results. In order to obtain class-conditional generation, it was suggested to guide the diffusion pr…

DenoisingImage Generation

Rethinking Oversaturation in Classifier-Free Guidance via Low Frequency

2025-06-26 · Kaiyu Song, Hanjiang Lai

Classifier-free guidance (CFG) succeeds in condition diffusion models that use a guidance scale to balance the influence of conditional and unconditional terms. A high guidance scale is used to enhance the performance of…

Diffusion Classifier Guidance for Non-robust Classifiers

2025-07-01 · Philipp Vaeth, Dibyanshu Kumar, Benjamin Paassen, Magda Gregorová arxiv

Classifier guidance is intended to steer a diffusion process such that a given classifier reliably recognizes the generated data point as a certain class. However, most classifier guidance approaches are restricted to ro…

Stochastic Optimization

Diffusion Models Beat GANs on Image Synthesis

2021-05-11 · NeurIPS 2021 12 · Prafulla Dhariwal, Alex Nichol

We show that diffusion models can achieve image sample quality superior to the current state-of-the-art generative models. We achieve this on unconditional image synthesis by finding a better architecture through a serie…

Conditional Image GenerationDiversityImage Generation