ConceptGuard：具有遗忘与混淆缓解能力的持续个性化文本到图像生成
ConceptGuard: Continual Personalized Text-to-Image Generation with Forgetting and Confusion Mitigation
AI总结：
针对持续个性化文本到图像生成中的概念遗忘与混淆问题，本文提出 ConceptGuard，通过移位嵌入、概念绑定提示、记忆正则化及自适应优先级队列提升顺序概念学习性能。
摘要：
扩散模型个性化方法仅需极少量用户提供的图像便取得了令人瞩目的成果。然而，现有方法通常以集体方式定制概念，而现实世界应用往往需要按顺序整合概念。这种顺序性可能导致灾难性遗忘，即先前学习的概念丢失。本文研究持续个性化中的概念遗忘与概念混淆问题。为应对这些挑战，我们提出 ConceptGuard，这是一种综合性方法，结合了移位嵌入、概念绑定提示和记忆保持正则化，并辅以一个优先级队列，该队列能够自适应地更新不同概念的重要性和出现顺序。这些策略可以动态更新、解绑并学习先前概念之间的关系，从而缓解概念遗忘和混淆。通过全面实验，我们表明该方法在定量和定性分析中均一致且显著地优于所有基线方法。
英文摘要：
Diffusion customization methods have achieved impressive results with only a minimal number of user-provided images. However, existing approaches customize concepts collectively, whereas real-world applications often require sequential concept integration. This sequential nature can lead to catastrophic forgetting, where previously learned concepts are lost. In this paper, we investigate concept forgetting and concept confusion in the continual customization. To tackle these challenges, we present ConceptGuard, a comprehensive approach that combines shift embedding, concept-binding prompts and memory preservation regularization, supplemented by a priority queue which can adaptively update the importance and occurrence order of different concepts. These strategies can dynamically update, unbind and learn the relationship of the previous concepts, thus alleviating concept forgetting and confusion. Through comprehensive experiments, we show that our approach outperforms all the baseline methods consistently and significantly in both quantitative and qualitative analyses.
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。
