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
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.
CausalDisenSeg: A Causality-Guided Disentanglement Framework with Counterfactual Reasoning for Robust Brain Tumor Segmentation Under Missing Modalities
School of Information Engineering, Nanchang University(南昌大学信息工程学院);School of Mathematics and Computer Sciences, Nanchang University(南昌大学数学与计算机科学学院)
Causality-guided Prompt Learning for Vision-language Models via Visual Granulation
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences(多模态人工智能系统国家重点实验室,自动化研究所,中国科学院);School of Artificial Intelligence, University of Chinese Academy of Sciences(人工智能学院,中国科学院大学)
CT-Guided Spatially-varying Regularization for Voxel-Wise Deformable Whole-Body PET Registration
Institute of Medical Technology, Peking University Health Science Center(北京大学医学部医学技术研究所);Ren Ji Hospital, Shanghai Jiao Tong University(上海交通大学仁济医院);University of Oxford(牛津大学)
The Overfocusing Bias of Convolutional Neural Networks: A Saliency-Guided Regularization Approach
IRT Saint-Exupéry(圣埃克苏佩里技术研究院);IMT(法国国家矿业电信研究院);INSA Toulouse(图卢兹国立应用科学学院);ANITI Toulouse(图卢兹人工智能与数字技术研究所);Université Paul Sabatier(保罗萨巴蒂尔大学);ISAE-SUPAERO(法国高等航空航天学院);Université de Toulouse(图卢兹大学)
Landmark-Guided Cross-Speaker Lip Reading with Mutual Information Regularization
School of Life Science and Technology, University of Electronic Science and Technology of China(电子科技大学生命科学与技术学院);Defense Innovation Institute, Academy of Military Sciences(军事科学院国防创新研究院);Tianjin Artificial Intelligence Innovation Center(天津人工智能创新中心);High-tech Institute of Qingzhou(青州高新技术研究院)
Double-Uncertainty Guided Spatial and Temporal Consistency Regularization Weighting for Learning-based Abdominal Registration
The Chinese University of Hong Kong(香港中文大学);Brigham and Women’s Hospital(布莱根妇女医院);Harvard Medical School(哈佛医学院);Tencent Jarvis Lab(腾讯医疗健康(深圳)有限公司(腾讯医疗AI实验室/腾讯天衍实验室));Tsinghua University(清华大学);Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院)
A Regularization-Guided Equivariant Approach for Image Restoration
School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an, China(西安交通大学数学与统计学学院);Macau University of Science and Technology, Taipa, Macao(澳门科学技术大学);Pengcheng Laboratory, Shenzhen, China(鹏城实验室)
DepthMatch: Semi-Supervised RGB-D Scene Parsing through Depth-Guided Regularization
College of Electronics & Information Engineering, Shanghai Institute of Intelligent Science and Technology, Shanghai Research Institute for Intelligent Autonomous Systems, the State Key Laboratory of Intelligent Autonomous Systems, and Frontiers Science Center for Intelligent Autonomous Systems, Tongji University(电子信息工程学院,上海智能科学与技术研究院,上海智能自主系统研究所以及智能自主系统国家重点实验室和智能自主系统前沿科学中心,同济大学)
Detection-Guided Deep Learning-Based Model with Spatial Regularization for Lung Nodule Segmentation
Department of Mathematics, Applied Mathematics, and Statistics, Case Western Reserve University(数学、应用数学与统计学系,凯斯西储大学);Department of Biomedical Engineering, Lerner Research Institute, Cleveland Clinic(生物医学工程系,勒纳研究学院,克利夫兰诊所);Imaging Institute, Cleveland Clinic(影像研究所,克利夫兰诊所);Department of Biomedical Engineering, Case Western Reserve University(生物医学工程系,凯斯西储大学)
Pan-denoising: Guided Hyperspectral Image Denoising via Weighted Represent Coefficient Total Variation
School of Mathematics and Statistics, Northwestern Polytechnical University(西北工业大学数学与统计学院);Research and Development Institute of Northwestern Polytechnical University in Shenzhen(西北工业大学深圳研究院)
DOMINO++: Domain-aware Loss Regularization for Deep Learning Generalizability
University of Florida (UF)(佛罗里达大学);Torch Technologies, LLC(Torch科技有限责任公司);McKnight Brain Institute(麦克奈特脑研究所);College of Public Health and Health Professions(公共卫生与健康职业学院);College of Medicine(医学院);United States Air Force Research Laboratory(美国空军研究实验室);Herbert Wertheim College of Engineering(赫伯特·韦特海姆工程学院);Department of Biomedical Engineering(生物医学工程系);Department of Clinical and Health Psychology(临床与健康心理学系);Department of Neuroscience(神经科学系);Department of Electrical and Computer Engineering(电气与计算机工程系);Department of Computer Information and Science and Engineering(计算机信息与工程系)