优化编码器：重新思考神经场的二阶元学习

中文摘要 AI 辅助

条件神经场连续地表示信号，但其有效性取决于如何从观测数据中推断条件潜在表示。在元学习中，这种编码通过解码器诱导的梯度更新发生，将表示学习直接与解码器设计联系起来。我们通过将潜在优化解释为优化编码器来形式化这一联系，统一了二阶微分、潜在参数化和任务监督的作用。这一概念使得二阶元学习能够对编码过程和解码器进行端到端训练，并阐明了哪些学习路径被一阶近似所丢弃。在此观点指导下，我们引入了注意力潜在场（MetaLF），一种基于等变变换器的神经场，通过自注意力对潜在点云进行上下文化。这些交互塑造了场预测和构建其表示的更新，使局部观测能够为连贯的非局部结构提供信息。将内部编码目标与外部任务监督分离，在端到端元学习框架内统一了重建、分类和分割，在测试时仅使用重建驱动的潜在适应。在多项式场上的受控实验将潜在协调与较低的有效秩和与底层函数空间的更强对齐联系起来。在图像和3D形状重建中，MetaLF在三到五次梯度更新内提高了保真度，同时支持跨图像、形状和体积的语义预测。总之，这些发现将优化编码器视角定位为围绕表示如何构建、协调和使用来设计神经场的统一基础。

英文摘要

Conditional neural fields represent signals continuously, but their effectiveness depends on how the conditional latent representations are inferred from observed data. In meta-learning, this encoding occurs through gradient updates induced by the decoder, tying representation learning directly to decoder design. We formalize this connection by interpreting latent optimization as an optimization encoder, unifying the roles of second-order differentiation, latent parameterization, and task supervision. This concept enables second-order meta-learning for end-to-end training of the encoding procedure alongside the decoder, and clarifies which learning pathway first-order approximations discard. Guided by this view, we introduce Attentive Latent Fields (MetaLF), an equivariant transformer-based neural field that contextualizes a latent pointcloud through self-attention. These interactions shape both field predictions and the updates that construct their representation, allowing local observations to inform coherent non-local structure. Disentangling the inner encoding objective from outer task supervision unifies reconstruction, classification, and segmentation within an end-to-end meta-learning framework, using reconstruction-only latent adaptation at test time. Controlled experiments on polynomial fields link latent coordination to lower effective rank and stronger alignment with the underlying function space. Across image and 3D shape reconstruction, MetaLF improves fidelity within three to five gradient updates, while supporting semantic prediction across images, shapes, and volumes. Together, these findings position the optimization encoder perspective as a unified basis for designing neural fields around how representations are constructed, coordinated, and used.

发表机构

• Weill Cornell Medicine（威尔康奈尔医学院）
• Cornell Tech（康奈尔科技学院）
• Amsterdam UMC（阿姆斯特丹大学医学中心）

机构由 AI 辅助整理，请以论文原文为准。