Where Culture Fades: Revealing the Cultural Gap in Text-to-Image Generation
Shi, Chuancheng, Li, Shangze, Guo, Shiming, Xie, Simiao, Wu, Wenhua, Dou, Jingtong, Wu, Chao, Xiao, Canran 等 12 位作者
原文摘要
Multilingual text-to-image (T2I) models have advanced rapidly in terms of visual realism and semantic alignment, and are now widely utilised. Yet outputs vary across cultural contexts: because language carries cultural connotations, images synthesized from multilingual prompts should preserve cross-lingual cultural consistency. We conduct a comprehensive analysis showing that current T2I models often produce culturally neutral or English-biased results under multilingual prompts.Analyses of two representative models indicate that the issue stems not from missing cultural knowledge but from insufficient activation of culture-related representations. We propose a probing method that localizes culture-sensitive signals to a small set of neurons in a few fixed layers. Guided by this finding, we introduce two complementary alignment strategies: (1) inference-time cultural activation that amplifies the identified neurons without backbone fine-tuned; and (2) layer-targeted cultural enhancement that updates only culturally relevant layers. Experiments on our CultureBench demonstrate consistent improvements over strong baselines in cultural consistency while preserving fidelity and diversity.
cs.CV
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表