arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.20355cs.CVcs.AI
收藏

CURVE:通过不确定性引导的正则化学习因果启发的不变表示以实现稳健的场景理解

CURVE: Learning Causality-Inspired Invariant Representations for Robust Scene Understanding via Uncertainty-Guided Regularization

Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai, China(上海智能自主系统研究院,同济大学);Guohao School, Tongji University, Shanghai, China(国豪学院,同济大学);School of Automotive Studies, Tongji University, Shanghai, China(汽车研究学院,同济大学);College of Electronics and Information Engineering, Tongji University, Shanghai, China(电子与信息工程学院,同济大学)

Yue Liang, Jiatong Du, Ziyi Yang, Yanjun Huang, Hong Chen

AI总结:

CURVE通过结合变分不确定性建模和不确定性引导的结构正则化,学习因果启发的不变表示,以提升场景理解的鲁棒性和分布外泛化能力。

摘要:

场景图提供了结构化的场景理解抽象,但它们常常过度拟合虚假相关性,严重阻碍了分布外泛化。为了解决这一限制,我们提出了CURVE,一个受因果启发的框架,整合了变分不确定性建模与不确定性引导的结构正则化,以抑制高方差、环境特定的关系。具体来说,我们应用原型条件去偏处理,以分离不变交互动态与环境依赖变化,促进稀疏且领域稳定的拓扑结构。实证上,我们在零样本迁移和低数据仿真到现实适应中评估了CURVE,验证了其学习领域稳定的稀疏拓扑结构和提供可靠不确定性估计的能力,以支持在分布偏移下的风险预测。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑