让生成模型同时学多个概念还不忘旧知识，提升个性化生成稳定性。
Forget Less by Learning Together through Concept Consolidation
- 通过概念间相互引导的机制，实现无序并发学习。
- 在十项任务中平均提升2%以上图像对齐得分，遗忘显著减少。
- 适合需要持续添加新个性内容的生成模型应用。
定制化扩散模型（CDMs）因其强大的个性化生成能力受到广泛关注。然而，现有CDMs在持续学习新概念时面临灾难性遗忘问题。以往工作多在固定顺序下进行序列学习，忽视概念间的相互作用。本文提出一种新框架——忘得少：共同学习（FL2T），支持并发、无序的概念学习，并缓解灾难性遗忘。具体地，引入集合不变的跨概念学习模块，利用代理指导跨概念特征选择，提升知识保留与迁移能力。借助概念间引导，方法在保留旧概念的同时高效融入新概念。在三个数据集上的大量实验表明，该方法显著提升概念保留率，有效缓解遗忘，在十项任务中平均CLIP图像对齐得分提升至少2%。
原文摘要 · Abstract (English)
Custom Diffusion Models (CDMs) have gained significant attention due to their remarkable ability to personalize generative processes. However, existing CDMs suffer from catastrophic forgetting when continuously learning new concepts. Most prior works attempt to mitigate this issue under the sequential learning setting with a fixed order of concept inflow and neglect inter-concept interactions. In this paper, we propose a novel framework - Forget Less by Learning Together (FL2T) - that enables concurrent and order-agnostic concept learning while addressing catastrophic forgetting. Specifically, we introduce a set-invariant inter-concept learning module where proxies guide feature selection across concepts, facilitating improved knowledge retention and transfer. By leveraging inter-concept guidance, our approach preserves old concepts while efficiently incorporating new ones. Extensive experiments, across three datasets, demonstrates that our method significantly improves concept retention and mitigates catastrophic forgetting, highlighting the effectiveness of inter-concept catalytic behavior in incremental concept learning of ten tasks with at least 2% gain on average CLIP Image Alignment scores.
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。