ヒューマノイドに着想を得た因果表現学習によるドメイン汎化
Humanoid-inspired Causal Representation Learning for Domain Generalization
人間の視覚処理を模した構造的因果モデル(HSCM)を提案し、色・テクスチャ・形状などの画像属性を分離・再重み付けすることで、ドメイン汎化性能と解釈性を向上させた。
著者: Ze Tao, Jian Zhang, Haowei Li, Xianshuai Li, Yifei Peng, Xiyao Liu, Senzhang Wang, Chao Liu, Sheng Ren, Shichao Zhang
分類: cs.AI, cs.LG
原文アブストラクト
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.