受人类智能启发的因果建模方法，提升模型跨域泛化能力。
Humanoid-inspired Causal Representation Learning for Domain Generalization
- 模仿人类视觉层级处理机制，建模图像属性间的细粒度因果关系。
- 通过解耦重加权颜色、纹理、形状等属性，显著提升跨域性能。
- 适合需要高鲁棒性与可解释性的复杂环境下的模型迁移任务。
本文提出一种受人类智能启发的结构化因果模型（HSCM），旨在克服传统领域泛化模型的局限性。不同于依赖统计方法捕捉数据-标签关联并学习扭曲不变表示的方法，HSCM 模仿人类视觉系统的层次化处理与多层级学习机制，聚焦于建模细粒度的因果机制。通过解耦并重加权颜色、纹理、形状等关键图像属性，HSCM 在多样领域间实现更强的泛化能力，确保模型在动态复杂环境中的稳健表现与可解释性。理论与实证评估均表明，该方法优于现有领域泛化模型，为捕捉因果关系提供了更严谨的框架。代码已开源：https://github.com/lambett/HSCM。
原文摘要 · Abstract (English)
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.
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。