Humanoid-inspired Causal Representation Learning for Domain Generalization
Preprint
Abstract
This paper proposes the Humanoid-inspired Structural Causal Model (HSCM), a novel causal framework inspired by human intelligence, designed to overcome the limitations of conventional domain generalization models. Unlike approaches that rely on statistics to capture data-label dependencies and learn distortion-invariant representations, HSCM replicates the hierarchical processing and multi-level learning of human vision systems, focusing on modeling fine-grained causal mechanisms. By disentangling and reweighting key image attributes such as color, texture, and shape, HSCM enhances generalization across diverse domains, ensuring robust performance and interpretability. Leveraging the flexibility and adaptability of human intelligence, our approach enables more effective transfer and learning in dynamic, complex environments. Through both theoretical and empirical evaluations, we demonstrate that HSCM outperforms existing domain generalization models, providing a more principled method for capturing causal relationships and improving model robustness. The code is available at https://github.com/lambett/HSCM.Keywords
All Related Versions
This publication has 13 references indexed in Scilit:
- Domain Generalization Study of Empirical Risk Minimization From Causal PerspectivesIEEE Transactions on Multimedia, 2025
- Decomposing causality into its synergistic, unique, and redundant componentsNature Communications, 2024
- MMAE: A universal image fusion method via mask attention mechanismPattern Recognition, 2024
- Fusion of Explainable Deep Learning Features Using Fuzzy Integral in Computer VisionIEEE Transactions on Fuzzy Systems, 2024
- Generalized Out-of-Distribution Detection: A SurveyInternational Journal of Computer Vision, 2024
- Visual temporal attention from perception to computationNature Reviews Psychology, 2024
- Generalizing to Unseen Domains: A Survey on Domain GeneralizationIEEE Transactions on Knowledge and Data Engineering, 2022
- Causal Inference Using the Algorithmic Markov ConditionIEEE Transactions on Information Theory, 2010
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- A database for handwritten text recognition researchIEEE Transactions on Pattern Analysis and Machine Intelligence, 1994