Salvato in:
Dettagli Bibliografici
Autori principali: Tao, Ze, Zhang, Jian, Li, Haowei, Li, Xianshuai, Peng, Yifei, Liu, Xiyao, Wang, Senzhang, Liu, Chao, Ren, Sheng, Zhang, Shichao
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2510.16382
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911218485166080
author Tao, Ze
Zhang, Jian
Li, Haowei
Li, Xianshuai
Peng, Yifei
Liu, Xiyao
Wang, Senzhang
Liu, Chao
Ren, Sheng
Zhang, Shichao
author_facet Tao, Ze
Zhang, Jian
Li, Haowei
Li, Xianshuai
Peng, Yifei
Liu, Xiyao
Wang, Senzhang
Liu, Chao
Ren, Sheng
Zhang, Shichao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_16382
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Humanoid-inspired Causal Representation Learning for Domain Generalization
Tao, Ze
Zhang, Jian
Li, Haowei
Li, Xianshuai
Peng, Yifei
Liu, Xiyao
Wang, Senzhang
Liu, Chao
Ren, Sheng
Zhang, Shichao
Artificial Intelligence
Machine Learning
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.
title Humanoid-inspired Causal Representation Learning for Domain Generalization
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2510.16382