提出无纠缠注意力机制，让文生图模型生成更公平的图像。
Fair Generation without Unfair Distortions: Debiasing Text-to-Image Generation with Entanglement-Free Attention
- 通过随机采样目标属性并调整交叉注意力，实现精准去偏。
- 在消除性别/种族偏见的同时，保持背景等非目标属性不变。
- 适合关注生成公平性、避免无意分布偏移的研究者与应用方。
基于扩散的文生图模型虽能生成高质量图像，但常存在性别、种族及社会经济地位等社会偏见，可能强化刻板印象。现有去偏方法常出现属性纠缠问题：调整偏见相关属性（如种族）时，意外改变无关属性（如背景），导致分布偏移。为此，本文提出无纠缠注意力（EFA）：推理时随机采样目标属性（如白人、黑人、亚洲人），并在特定层调整交叉注意力以融入该属性，实现目标属性的公平分布。大量实验表明，EFA在减轻偏见的同时有效保留非目标属性，维持原始模型的输出分布与生成能力。
原文摘要 · Abstract (English)
Recent advancements in diffusion-based text-to-image (T2I) models have enabled the generation of high-quality and photorealistic images from text. However, they often exhibit societal biases related to gender, race, and socioeconomic status, thereby potentially reinforcing harmful stereotypes and shaping public perception in unintended ways. While existing bias mitigation methods demonstrate effectiveness, they often encounter attribute entanglement, where adjustments to attributes relevant to the bias (i.e., target attributes) unintentionally alter attributes unassociated with the bias (i.e., non-target attributes), causing undesirable distribution shifts. To address this challenge, we introduce Entanglement-Free Attention (EFA), a method that accurately incorporates target attributes (e.g., White, Black, and Asian) while preserving non-target attributes (e.g., background) during bias mitigation. At inference time, EFA randomly samples a target attribute with equal probability and adjusts the cross-attention in selected layers to incorporate the sampled attribute, achieving a fair distribution of target attributes. Extensive experiments demonstrate that EFA outperforms existing methods in mitigating bias while preserving non-target attributes, thereby maintaining the original model's output distribution and generative capacity.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。