提出新方法自动发现数据内在对称性，无需预设姿态空间
RECON: Robust symmetry discovery via Explicit Canonical Orientation Normalization
- 通过右平移修正任意初始姿态，实现数据自适应的规范表示
- 无需训练即可发现实例特有姿态分布，提升模型对异常姿态的检测能力
- 可直接接入预训练模型，增强其群不变性，适合部署优化场景
真实世界数据常具有未知且实例特定的对称性，通常不严格符合预先固定的变换群 $G$。类别-姿态分解旨在通过将输入分解为不变特征和相对于训练依赖的任意规范表示定义的姿态 $g o G$，实现表征解耦。我们提出 RECON，一种类-姿态无关的规范方向归一化方法，通过简单的右平移纠正任意规范表示，生成自然且与数据对齐的规范形式。该方法可实现：(i) 无监督发现实例特有姿态分布，(ii) 检测分布外姿态，(iii) 提供即插即用的测试时规范归一化层。该层可附加于任意预训练模型之上，注入群不变性，无需重训练即可提升性能。我们在图像和分子构象数据集上验证，实现了准确的对称性发现，并在下游分类任务中达到或超越现有归一化方法的效果。
原文摘要 · Abstract (English)
Real world data often exhibits unknown, instance-specific symmetries that rarely exactly match a transformation group $G$ fixed a priori. Class-pose decompositions aim to create disentangled representations by factoring inputs into invariant features and a pose $g\in G$ defined relative to a training-dependent, arbitrary canonical representation. We introduce RECON, a class-pose agnostic canonical orientation normalization that corrects arbitrary canonicals via a simple right translation, yielding natural, data-aligned canonicalizations. This enables (i) unsupervised discovery of instance-specific pose distributions, (ii) detection of out-of-distribution poses and (iii) a plug-and-play test-time canonicalization layer. This layer can be attached on top of any pre-trained model to infuse group invariance, improving its performance without retraining. We validate on images and molecular ensembles, demonstrating accurate symmetry discovery, and matching or outperforming other canonicalizations in downstream classification.
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。