.png){kind=icon}
Return
Rethinking Noise Sampling in Class-Imbalanced Diffusion Models
.png){kind=icon}
PRE
AI
DOI：10.1109/TIP.2024.3485484.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In the practical application of image generation, dealing with long-tailed data distributions is a common challenge for diffusion-based generative models. To tackle this issue, we investigate the head-class accumulation effect in diffusion models' latent space, particularly focusing on its correlation to the noise sampling strategy. Our experimental analysis indicates that employing a consistent sampling distribution for the noise prior across all classes leads to a significant bias towards head classes in the noise sampling distribution, which results in poor quality and diversity of the generated images. Motivated by this observation, we propose a novel sampling strategy named Bias-aware Prior Adjusting (BPA) to debias diffusion models in the class-imbalanced scenario. With BPA, each class is automatically assigned an adaptive noise sampling distribution prior during training, effectively mitigating the influence of class imbalance on the generation process. Extensive experiments on several benchmarks demonstrate that images generated using our proposed BPA showcase elevated diversity and superior quality.
Keywords:
Noise
Diffusion models
Head
Training
Tail
Data models
Training data
Process control
Noise measurement
Interpolation
Long-tailed learning
diffusion model
image generation
Journal
IF:
13.7
Papers:
1.0W
Citations:
8.4W
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSave
ShareSaveShareSaveShareSave
View more