Generating on Generated: An Approach Towards Self-Evolving Diffusion Models
Recursive Self-Improvement (RSI) enables intelligence systems to autonomously refine their capabilities. This paper explores the application of RSI in text-to-image diffusion models, addressing the challenge of training collapse caused by synthetic data. We identify two key factors contributing to this collapse: the lack of perceptual alignment and the accumulation of generative hallucinations. To mitigate these issues, we propose three strategies: (1) a prompt construction and filtering pipeline designed to facilitate the generation of perceptual aligned data, (2) a preference sampling method to identify human-preferred samples and filter out generative hallucinations, and (3) a distribution-based weighting scheme to penalize selected samples with hallucinatory errors. Our extensive experiments validate the effectiveness of these approaches.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Diffusion Curriculum: Synthetic-to-Real Generative Curriculum Learning via Image-Guided Diffusion
Low-quality or scarce data has posed significant challenges for training deep neural networks in practice. While classical data augmentation cannot contribute very different new data, diffusion models opens up a new door…
Data AugmentationImage GenerationSelf-Evolving AIConfidence-Orchestrated Self-Evolution against Uncertain LLM Feedback
Self-evolving large language models (LLMs) learn by generating their own training tasks and solutions, reducing reliance on human-curated supervision. However, in many reasoning domains, the model must also validate gene…
DiffusionFace: Towards a Comprehensive Dataset for Diffusion-Based Face Forgery Analysis
The rapid progress in deep learning has given rise to hyper-realistic facial forgery methods, leading to concerns related to misinformation and security risks. Existing face forgery datasets have limitations in generatin…
Image GenerationMisinformationAttentive Eraser: Unleashing Diffusion Model's Object Removal Potential via Self-Attention Redirection Guidance
Recently, diffusion models have emerged as promising newcomers in the field of generative models, shining brightly in image generation. However, when employed for object removal tasks, they still encounter issues such as…
Image GenerationObjectANCHOR: An External LLM-Driven Supervisory Module Facilitating Healthy Evolution in Self-Evolving Systems
Self-evolving agents improve through continual self-play and self-generated learning signals, but their internally generated tasks and verifier signals provide limited coverage of phase-level errors, allowing capability …
Mathematical Reasoning