ACE-LoRA：适应性正交解耦用于持续图像编辑
ACE-LoRA: Adaptive Orthogonal Decoupling for Continual Image Editing
AI总结：
ACE-LoRA通过动态正则化框架解决持续图像编辑中的灾难性遗忘问题，采用适应性正交解耦和历史信息压缩策略，提出首个全面的CIE-Bench基准，验证方法在指令忠实度、视觉真实性和抗遗忘性上的优势。
摘要：
最先进的扩散模型常依赖参数高效微调来执行特定图像编辑任务。然而，现实应用需要持续适应新任务同时保持先前学习的知识。尽管实用性很强，持续学习在图像编辑中仍被广泛忽视。我们提出了ACE-LoRA，一种动态正则化框架，有效缓解灾难性遗忘。ACE-LoRA利用适应性正交解耦来识别并正交化任务干扰，并引入秩不变历史信息压缩策略以解决持续更新中的可扩展性问题。为促进图像编辑中的持续学习并提供标准化评估协议，我们引入CIE-Bench，首个该领域的综合性基准。CIE-Bench涵盖多样且实际相关的图像编辑场景，具有平衡难度水平，有效暴露现有模型的局限性，同时与参数高效微调兼容。大量实验表明，我们的方法在指令忠实度、视觉真实性和抗遗忘性方面均优于现有基线，为图像编辑中的持续学习奠定了坚实基础。
英文摘要：
State-of-the-art diffusion models often rely on parameter-efficient fine-tuning to perform specialized image editing tasks. However, real-world applications require continual adaptation to new tasks while preserving previously learned knowledge. Despite the practical necessity, continual learning for image editing remains largely underexplored. We propose ACE-LoRA, a dynamic regularization framework for continual image editing that effectively mitigates catastrophic forgetting. ACE-LoRA leverages Adaptive Orthogonal Decoupling to identify and orthogonalize task interference, and introduces a Rank-Invariant Historical Information Compression strategy to address scalability issues in continual updates. To facilitate continual learning in image editing and provide a standardized evaluation protocol, we introduce CIE-Bench, the first comprehensive benchmark in this domain. CIE-Bench encompasses diverse and practically relevant image editing scenarios with a balanced level of difficulty to effectively expose limitations of existing models while remaining compatible with parameter-efficient fine-tuning. Extensive experiments demonstrate that our method consistently outperforms existing baselines in terms of instruction fidelity, visual realism, and robustness to forgetting, establishing a strong foundation for continual learning in image editing.
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。
