通过不确定性引导正则化，让场景理解模型更鲁棒。
CURVE: Learning Causality-Inspired Invariant Representations for Robust Scene Understanding via Uncertainty-Guided Regularization
- 用不确定性建模抑制环境特有关系，学习不变表示。
- 在零样本迁移和少样本模拟到真实场景中表现优异。
- 适合需要可靠风险预测的高可靠性场景理解任务。
场景图提供了场景理解的结构化抽象，但常因捕捉虚假相关性而过拟合，严重损害分布外泛化能力。为此，我们提出CURVE，一种受因果启发的框架，将变分不确定性建模与不确定性引导的结构正则化相结合，以抑制高方差、环境依赖的关系。具体而言，采用原型条件去偏方法，分离出不变的交互动态与环境相关变化，促进稀疏且域稳定的拓扑结构。实验上，我们在零样本迁移和低数据量模拟到真实场景适应任务中评估CURVE，验证其能学习域稳定的稀疏拓扑，并提供可靠的不确定性估计，支持分布漂移下的风险预测。
原文摘要 · Abstract (English)
Scene graphs provide structured abstractions for scene understanding, yet they often overfit to spurious correlations, severely hindering out-of-distribution generalization. To address this limitation, we propose CURVE, a causality-inspired framework that integrates variational uncertainty modeling with uncertainty-guided structural regularization to suppress high-variance, environment-specific relations. Specifically, we apply prototype-conditioned debiasing to disentangle invariant interaction dynamics from environment-dependent variations, promoting a sparse and domain-stable topology. Empirically, we evaluate CURVE in zero-shot transfer and low-data sim-to-real adaptation, verifying its ability to learn domain-stable sparse topologies and provide reliable uncertainty estimates to support risk prediction under distribution shifts.
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。