Learning domain-invariant semantic representations is crucial for achieving domain generalization (DG), where a model is required to perform well on unseen target domains. One critical challenge is that standard training often results in entangled semantic and domain-specific features. Previous works suggest formulating the problem from a causal perspective and solving the entanglement problem by enforcing marginal independence between the causal (\ie semantic) and non-causal (\ie domain-specific) features. Despite its simplicity, the basic marginal independent-based idea alone may be insufficient to identify the causal feature. By d-separation, we observe that the causal feature can be further characterized by being independent of the domain conditioned on the object, and we propose the following two strategies as complements for the basic framework.
First, the observation implicitly implies that for the same object, the causal feature should not be associated with the non-causal feature, revealing that the common practice of obtaining the two features with a shared base feature extractor and two lightweight prediction heads might be inappropriate. To meet the constraint, we propose a simple early-branching structure, where the causal and non-causal feature obtaining branches share the first few blocks while diverging thereafter, for better structure design; Second, the observation implies that the causal feature remains invariant across different domains for the same object. To this end, we suggest that augmentation should be incorporated into the framework to better characterize the causal feature, and we further suggest an effective random domain sampling scheme to fulfill the task. Theoretical and experimental results show that the two strategies are beneficial for the basic marginal independent-based framework. Code is available at \url{https://github.com/liangchen527/CausEB}.
Causality-Inspired Taxonomy for Explainable Artificial Intelligence
INESC TEC;Faculty of Engineering - University of Porto(波尔图大学工程学院);Vision-Box;Utrecht University(乌得勒支大学);The Netherlands Cancer Institute(荷兰癌症研究所);Michigan State University(密歇根州立大学)
A Causality-Inspired Model for Intima-Media Thickening Assessment in Ultrasound Videos
School of Biological Science and Medical Engineering, Southeast University(东南大学生物科学与医学工程学院);School of Computer Science and Engineering, Southeast University(东南大学计算机科学与工程学院);Peking Union Medical College Hospital, Chinese Academy of Medical Sciences(中国医学科学院北京协和医学院医院)
Causal-Inspired Multitask Learning for Video-Based Human Pose Estimation
College of Computer Science and Technology, Jilin University(吉林大学计算机科学与技术学院);College of Computer Science and Technology, Zhejiang Gongshang University(浙江工商大学计算机科学与技术学院);Public Computer Education and Research Center, Jilin University(吉林大学公共计算机教育与研究中心);Zhejiang University(浙江大学);Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security(杭州高新区(滨江)区块链与数据安全研究院)
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)
Causal Disentanglement-Inspired Degradation Representation Learning for Full-Reference Image Quality Assessment
School of Computing and Artificial Intelligence, Southwest Jiaotong University(计算机与人工智能学院,西南交通大学);School of Transportation and Logistics, Southwest Jiaotong University(交通运输与物流学院,西南交通大学);School of Physics, Northeast Normal University(物理学院,东北师范大学);School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics(计算机与人工智能学院,江西财经大学);School of Information Management, Jiangxi University of Finance and Economics(信息管理学院,江西财经大学)
Deconfounding Causal Inference through Two-Branch Framework with Early-Forking for Sensor-Based Cross-Domain Activity Recognition
School of Electrical and Automation Engineering(电气与自动化工程学院);Nanjing Normal University(南京师范大学);Department of Statistics and Data Science(统计与数据科学系);Southern University of Science and Technology(南方科技大学);School of Cyber Science and Engineering(网络科学与工程学院);Southeast University(东南大学);School of Computer Science and Engineering(计算机科学与工程学院)
Rethinking Radiology Report Generation via Causal Inspired Counterfactual Augmentation
Nanjing University(南京大学);South China Agricultural University(华南农业大学);Nankai University(南开大学);The First Affiliated Hospital, Sun Yat-sen University(中山大学附属第一医院);Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院)