New Noise Schedule Improves Diffusion Models for Imbalanced Data
▶ The 2-minute explainer
Key takeaways
- Diffusion models struggle with imbalanced datasets, leading to poor generation for rare classes.
- A new CFRG noise schedule assigns larger noise to low-frequency classes.
- This improves score estimation and prevents high-frequency class dominance.
- Significant improvements in image and text-to-image generation on imbalanced data are observed.
Who benefits
Summary
Researchers introduce the Class-frequency Guided (CFRG) noise schedule for diffusion models, which assigns larger-scale noises to low-frequency classes. This method significantly improves generation quality and diversity for imbalanced datasets by addressing issues of inaccurate score estimation and high-frequency class dominance.
Why it matters
Professionals developing generative AI models, especially for real-world datasets that are often imbalanced, can use this technique to produce higher-quality and more diverse outputs, improving model fairness and utility.
How to implement this in your domain
- 1Analyze existing diffusion model training pipelines for performance on imbalanced datasets.
- 2Implement the Class-frequency Guided (CFRG) noise schedule in custom diffusion models.
- 3Experiment with different noise scaling strategies based on class frequency for specific datasets.
- 4Evaluate the impact of CFRG on generation quality, diversity, and fairness metrics for low-frequency classes.
Original post by Jiequan Cui, Beier Zhu, Qingshan Xu, Xiaojuan Qi, Bei Yu, Hanwang Zhang
"arXiv:2606.27696v1 Announce Type: new Abstract: In this paper, we are the first to examine the correlations between class frequency and the multi-scale noise schedule within diffusion models. For score-based generative models, low-density regions often lead to inaccurately estima…"
View on XOriginally posted by Jiequan Cui, Beier Zhu, Qingshan Xu, Xiaojuan Qi, Bei Yu, Hanwang Zhang on X · view source
Want to go deeper?
Turn these trends into skills with Learnijoy's hands-on AI & tech courses.
Explore coursesMore in AI Research
Children Share Perspectives on Artificial Intelligence Use
A study explored children's views on artificial intelligence, revealing varied uses from academic assistance to creative applications, challenging initial assumptions about their engagement with the technology.
Task-Vector Interference in Merged LLMs Driven by Orientation, Not Magnitude.
This research reveals that interference in merged language models, often attributed to magnitude, is primarily driven by the orientation of task-vectors. It demonstrates that erasing interference along specific directions causally removes its effects, while magnitude-based interventions are insufficient and inconsistent.
New Method Detects Gradual GNSS Spoofing in Autonomous Driving.
This paper proposes a causal high-order liquid evidence framework to detect gradual GNSS spoofing attacks in autonomous driving. By modeling the evolution of GNSS-motion inconsistency with multiple evidence streams and adaptive liquid encoders, the method achieves high F1-scores in detecting subtle spoofing.