Diminishing Stereotype Bias in Image Generation Model using Reinforcemenlent Learning Feedback

원문 초록

This study addresses gender bias in image generation models using Reinforcement Learning from Artificial Intelligence Feedback (RLAIF) with a novel Denoising Diffusion Policy Optimization (DDPO) pipeline. By employing a pretrained stable diffusion model and a highly accurate gender classification Transformer, the research introduces two reward functions: Rshift for shifting gender imbalances, and Rbalance for achieving and maintaining gender balance. Experiments demonstrate the effectiveness of this approach in mitigating bias without compromising image quality or requiring additional data or prompt modifications. While focusing on gender bias, this work establishes a foundation for addressing various forms of bias in AI systems, emphasizing the need for responsible AI development. Future research directions include extending the methodology to other bias types, enhancing the RLAIF pipeline's robustness, and exploring multi-prompt fine-tuning to further advance fairness and inclusivity in AI.