arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2401.05779cs.CV
收藏

扩散模型中不良影响的消除

Erasing Undesirable Influence in Diffusion Models

Monash University(莫纳什大学);Qualcomm(高通公司)

Jing Wu, Trung Le, Munawar Hayat, Mehrtash Harandi

AI总结:

本文提出EraseDiff算法,通过约束优化和一阶求解在扩散模型中消除不良信息,同时保留模型在保留数据上的效用,实现遗忘与性能的最优平衡。

摘要:

扩散模型在生成高质量图像方面非常有效,但也带来了风险,例如无意中生成NSFW(不适合工作场所)内容。尽管已经提出了多种技术在保持整体性能的同时减轻扩散模型中的不良影响,但在这些目标之间取得平衡仍然具有挑战性。在这项工作中,我们提出了EraseDiff,这是一种旨在保留扩散模型在保留数据上的效用,同时移除与待遗忘数据相关的不良信息的算法。我们的方法利用价值函数将该任务形式化为一个约束优化问题,从而得到一个自然的一阶算法来求解该优化问题。通过改变生成过程以偏离真实去噪轨迹,我们在更新参数以实现保留的同时控制约束减少以确保有效消除,从而取得最优权衡。大量实验以及与最先进算法的全面比较表明,EraseDiff有效地保持了模型的效用、有效性和效率。

英文摘要:

Diffusion models are highly effective at generating high-quality images but pose risks, such as the unintentional generation of NSFW (not safe for work) content. Although various techniques have been proposed to mitigate unwanted influences in diffusion models while preserving overall performance, achieving a balance between these goals remains challenging. In this work, we introduce EraseDiff, an algorithm designed to preserve the utility of the diffusion model on retained data while removing the unwanted information associated with the data to be forgotten. Our approach formulates this task as a constrained optimization problem using the value function, resulting in a natural first-order algorithm for solving the optimization problem. By altering the generative process to deviate away from the ground-truth denoising trajectory, we update parameters for preservation while controlling constraint reduction to ensure effective erasure, striking an optimal trade-off. Extensive experiments and thorough comparisons with state-of-the-art algorithms demonstrate that EraseDiff effectively preserves the model's utility, efficacy, and efficiency.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑