UniNDM: A Unified Noise-driven Detection and Mitigation Framework Against Sexual Content in Text-to-Image Generation
UniNDM:文本到图像生成中针对性内容的统一噪声驱动检测与缓解框架
机构 * Institute of Artificial Intelligence, State Key Laboratory of Virtual Reality Technology and Systems, Beihang University(北京航空航天大学虚拟现实技术与系统国家重点实验室人工智能研究院) ; College of Artificial Intelligence, Tsinghua University(清华大学人工智能学院) ; Security Department, Alibaba Group(阿里巴巴集团安全部) ; School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-Sen University(中山大学深圳校区网络科学与技术学院)
AI总结 针对文本到图像生成易受隐式性提示影响的问题,提出UniNDM统一噪声驱动框架。利用早期预测噪声的可分离性开发轻量级检测器,引入噪声增强自适应负引导缓解问题,扩展到扩散变压器架构,实验显示比现有方法有显著改进。
Comments 18 pages, 10 figures, accepted by TPAMI