文化可及性图谱：通过功能映射调和物体多样性
Culture Affordance Atlas: Reconciling Object Diversity Through Functional Mapping
AI总结：
本文提出文化可及性图谱，通过功能映射调和物体多样性，减少经济绩效差距，提升低收入环境模型效果。
摘要：
文化塑造了人们使用的物体及其用途，但主流视觉-语言（VL）数据集经常表现出文化偏见，倾向于高收入、西方语境，这种不平衡降低了模型的泛化能力，并加剧了性能差距，尤其影响低收入和非西方社区。为解决这些差距，我们提出了一种新的以功能为中心的框架，通过不同文化和经济背景中物体所履行的功能来分类物体。我们通过创建文化可及性图谱来实现这一框架，这是对Dollar Street数据集的重新注释和文化导向的重新组织，覆盖46种功能和288种物体，公开可访问于https://lit.eecs.umich.edu/CultureAffordance-Atlas/index.html。通过使用CLIP模型进行广泛的经验分析，我们证明功能中心标签通过减少高收入和低收入群体之间的经济绩效差距（中位数减少6个百分点，统计显著），提高了对低收入环境模型的有效性。此外，我们的分析揭示了许多在主要VL数据集中被忽视的具有文化重要性的物体。我们的贡献为构建包容性的VL数据集和公平的AI系统提供了可扩展的路径。
英文摘要：
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 publicly available at https://lit.eecs.umich.edu/CultureAffordance-Atlas/index.html. 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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
