Culture Affordance Atlas: Reconciling Object Diversity Through Functional Mapping
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (46) · 39089-39097
DOI: 10.1609/aaai.v40i46.41256 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Joan Nwatu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
Culture shapes the objects people use and for what purposes, yet mainstream Vision-Language (VL) datasets frequently exhibit cultural biases, disproportionately favoring higher-income, Western contexts. This imbalance reduces model generalizability and perpetuates performance disparities, especially impacting lower-income and non-Western communities. To address these disparities, we propose a novel function-centric framework that categorizes objects by the functions they fulfill, across diverse cultural and economic contexts. We implement this framework by creating the Culture Affordance Atlas, a re-annotated and culturally grounded restructuring of the Dollar Street dataset spanning 46 functions and 288 objects. Through extensive empirical analyses using the CLIP model, we demonstrate that function-centric labels substantially reduce socioeconomic performance gaps between high and low-income groups by a median of 6 pp (statistically significant), improving model effectiveness for lower income contexts. Furthermore, our analyses reveals numerous culturally essential objects that are frequently overlooked in prominent VL datasets. Our contributions offer a scalable pathway toward building inclusive VL datasets and equitable AI systems.
Zitieren
APA
Nwatu, J., Bai, L., Ignat, O., & Mihalcea, R. (2026). Culture Affordance Atlas: Reconciling Object Diversity Through Functional Mapping. Proceedings of the AAAI Conference on Artificial Intelligence, 40(46), 39089-39097. https://doi.org/10.1609/aaai.v40i46.41256
Vancouver
Nwatu J, Bai L, Ignat O, Mihalcea R. Culture Affordance Atlas: Reconciling Object Diversity Through Functional Mapping. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(46):39089-39097. doi:10.1609/aaai.v40i46.41256
BibTeX
@article{Nwatu2026,
author = {Nwatu, Joan and Bai, Longju and Ignat, Oana and Mihalcea, Rada},
title = {Culture Affordance Atlas: Reconciling Object Diversity Through Functional Mapping},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {46},
pages = {39089--39097},
doi = {10.1609/aaai.v40i46.41256}
}
EUVIMED