挖掘属性子空间以实现3D基础模型的高效微调
Mining Attribute Subspaces for Efficient Fine-tuning of 3D Foundation Models
提出通过合成数据挖掘与不同变化类型（纹理、几何、相机运动、光照）关联的低秩适配子空间，并整合为更紧凑的子空间用于高效微调3D基础模型，为视觉领域提供了一种可复用的参数高效微调策略。
原文依据 Integrating them leads to a reduced LoRA subspace that enables efficient LoRA fine-tuning with improved prediction accuracy for downstream tasks.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论随着3D基础模型的出现，针对下游任务对其进行微调的兴趣日益增长，其中低秩适配（LoRA）是主流的微调范式。由于3D数据集在纹理、几何、相机运动和光照方面表现出明显的变化，存在一些有趣的基础问题：1）是否存在与每种变化类型相关联的LoRA子空间？2）这些子空间是否解耦（即相互正交）？3）如何有效地计算它们？本文为所有这些问题提供了答案。我们引入了一种稳健的方法，生成具有受控变化的合成数据集，在每个数据集上微调LoRA适配器，并提取与每种变化类型相关联的LoRA子空间。我们表明这些子空间近似解耦。将它们整合可得到一个缩减的LoRA子空间，该子空间能够实现高效的LoRA微调，并提高下游任务的预测精度。特别地，我们表明这种缩减的LoRA子空间尽管完全源自合成数据，却能泛化到真实数据集。消融实验验证了我们方法中各项选择的有效性。
英文原文摘要 1158 字符
With the emergence of 3D foundation models, there is growing interest in fine-tuning them for downstream tasks, where LoRA is the dominant fine-tuning paradigm. As 3D datasets exhibit distinct variations in texture, geometry, camera motion, and lighting, there are interesting fundamental questions: 1) Are there LoRA subspaces associated with each type of variation? 2) Are these subspaces disentangled (i.e., orthogonal to each other)? 3) How do we compute them effectively? This paper provides answers to all these questions. We introduce a robust approach that generates synthetic datasets with controlled variations, fine-tunes a LoRA adapter on each dataset, and extracts a LoRA subspace associated with each type of variation. We show that these subspaces are approximately disentangled. Integrating them leads to a reduced LoRA subspace that enables efficient LoRA fine-tuning with improved prediction accuracy for downstream tasks. In particular, we show that such a reduced LoRA subspace, despite being derived entirely from synthetic data, generalizes to real datasets. An ablation study validates the effectiveness of the choices in our approach.