Fine-Grained Generalization via Structuralizing Concept and Feature Space into Commonality, Specificity and Confounding
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (12) · 10394-10402
DOI: 10.1609/aaai.v40i12.38010 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zhen Wang und 4 weiteren Autor:innen.
Abstract (Originalsprache)
Fine-Grained Domain Generalization (FGDG) presents greater challenges than conventional domain generalization due to the subtle inter-class differences and relatively pronounced intra-class variations inherent in fine-grained recognition tasks. Under domain shifts, the model becomes overly sensitive to fine-grained cues, leading to the suppression of critical features and a significant drop in performance. Cognitive studies suggest that humans classify objects by leveraging both common and specific attributes, enabling accurate differentiation between fine-grained categories. However, current deep learning models have yet to incorporate this mechanism effectively. Inspired by this mechanism, we propose Concept-Feature Structuralized Generalization (CFSG). This model explicitly disentangles both the concept and feature spaces into three structured components: common, specific, and confounding segments. To mitigate the adverse effects of varying degrees of distribution shift, we introduce an adaptive mechanism that dynamically adjusts the proportions of common, specific, and confounding components. In the final prediction, explicit weights are assigned to each pair of components. Extensive experiments on three single-source benchmark datasets demonstrate that CFSG achieves an average performance improvement of 9.87% over baseline models and outperforms existing state-of-the-art methods by an average of 3.08%. Additionally, explainability analysis validates that CFSG effectively integrates multi-granularity structured knowledge and confirms that feature structuralization facilitates the emergence of concept structuralization.
Zitieren
APA
Wang, Z., Zhao, J., Wang, Q., Dong, Y., & Yu, W. (2026). Fine-Grained Generalization via Structuralizing Concept and Feature Space into Commonality, Specificity and Confounding. Proceedings of the AAAI Conference on Artificial Intelligence, 40(12), 10394-10402. https://doi.org/10.1609/aaai.v40i12.38010
Vancouver
Wang Z, Zhao J, Wang Q, Dong Y, Yu W. Fine-Grained Generalization via Structuralizing Concept and Feature Space into Commonality, Specificity and Confounding. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(12):10394-10402. doi:10.1609/aaai.v40i12.38010
BibTeX
@article{Wang2026,
author = {Wang, Zhen and Zhao, Jiaojiao and Wang, Qilong and Dong, Yongfeng and Yu, Wenlong},
title = {Fine-Grained Generalization via Structuralizing Concept and Feature Space into Commonality, Specificity and Confounding},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {12},
pages = {10394--10402},
doi = {10.1609/aaai.v40i12.38010}
}
EUVIMED