让扩散模型删掉危险概念，还能保持生成质量不下降
ACE: Concept Editing in Diffusion Models without Performance Degradation
- 用跨空投影技术精准删除危险概念
- 语义一致性提升24.56%，图像质量提升34.82%
- 仅需1%时间开销，适合实际部署
基于扩散的文生图模型虽能生成逼真图像，但存在生成不当内容的伦理风险。现有概念编辑方法难以在移除危险概念的同时保持模型通用生成能力。本文提出ACE方法，通过新颖的跨空投影机制，在精确擦除危险概念的同时维持高质量、语义一致的图像生成能力。大量实验表明，相比前沿基线，ACE平均提升语义一致性24.56%、图像生成质量34.82%，且仅需1%的时间成本。该结果凸显了概念编辑的实用价值，有助于缓解其潜在风险，推动该技术在更多场景的应用。代码已开源。
原文摘要 · Abstract (English)
Diffusion-based text-to-image models have demonstrated remarkable capabilities in generating realistic images, but they raise societal and ethical concerns, such as the creation of unsafe content. While concept editing is proposed to address these issues, they often struggle to balance the removal of unsafe concept with maintaining the model's general genera-tive capabilities. In this work, we propose ACE, a new editing method that enhances concept editing in diffusion models. ACE introduces a novel cross null-space projection approach to precisely erase unsafe concept while maintaining the model's ability to generate high-quality, semantically consistent images. Extensive experiments demonstrate that ACE significantly outperforms the advancing baselines,improving semantic consistency by 24.56% and image generation quality by 34.82% on average with only 1% of the time cost. These results highlight the practical utility of concept editing by mitigating its potential risks, paving the way for broader applications in the field. Code is avaliable at https://github.com/littlelittlenine/ACE-zero.git
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。