提出新方法，精准定位扩散模型生成中各概念的来源。
Concept-TRAK: Understanding how diffusion models learn concepts through concept-level attribution
- 用专用损失函数设计，分离特定概念的影响
- 在合成与真实数据上显著优于现有方法
- 适合关注版权与生成透明性的研究者
尽管扩散模型在图像生成方面表现优异，但其广泛应用引发了版权和模型透明度的关切。现有归因方法只能识别影响整张图像的训练样本，难以区分对特定元素（如风格或物体）的贡献，而这正是利益相关方关注的重点。为此，我们提出概念级归因方法 Concept-TRAK，通过引入专门的训练和效用损失函数，扩展影响力函数，以隔离特定概念的影响而非整体重建质量。我们在 Synthetic 与 CelebA-HQ 数据集上构建了新的概念归因基准，并在现有的 AbC 基准上进行评估，结果显示 Concept-TRAK 在概念级归因任务中显著优于先前方法。此外，我们还在真实世界的文本到图像生成中验证其在组合式和多概念提示下的适用性。
原文摘要 · Abstract (English)
While diffusion models excel at image generation, their growing adoption raises critical concerns about copyright issues and model transparency. Existing attribution methods identify training examples influencing an entire image, but fall short in isolating contributions to specific elements, such as styles or objects, that are of primary concern to stakeholders. To address this gap, we introduce concept-level attribution through a novel method called Concept-TRAK, which extends influence functions with a key innovation: specialized training and utility loss functions designed to isolate concept-specific influences rather than overall reconstruction quality. We evaluate Concept-TRAK on novel concept attribution benchmarks using Synthetic and CelebA-HQ datasets, as well as the established AbC benchmark, showing substantial improvements over prior methods in concept-level attribution scenarios. We further demonstrate its versatility on real-world text-to-image generation with compositional and multi-concept prompts.
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。