发现DALL-E2生成森林时存在区域偏见，且与真实森林分布不符。
Uncovering Regional Defaults from Photorealistic Forests in Text-to-Image Generation with DALL-E 2
- 通过层级区域生成与相似度对比，系统检测模型隐含的区域偏好。
- 模型生成的森林图像偏向特定区域，且这种倾向随尺度变化。
- 真实森林覆盖率高的地区未必被模型优先生成，提示地理偏差问题。
区域默认指文本到图像（T2I）基础模型在生成中倾向于过度描绘某些地理区域而忽略其他地区。本文提出一种可扩展的评估方法，通过基于区域层级的图像生成与跨层级相似性比较来揭示此类区域默认。实验以DALL-E 2为对象，要求其生成森林图像。选择森林作为具有区域性差异且可用空间统计特征描述的对象类别。在区域层级中，实验揭示了DALL-E 2中隐含的区域默认，其具有尺度依赖性及空间关联性。此外，发现这些隐含默认并不必然对应现实中森林覆盖最广的区域。研究结果强调需进一步探究T2I生成及其他生成式AI中的地理偏见问题。
原文摘要 · Abstract (English)
Regional defaults describe the emerging phenomenon that text-to-image (T2I) foundation models used in generative AI are prone to over-proportionally depicting certain geographic regions to the exclusion of others. In this work, we introduce a scalable evaluation for uncovering such regional defaults. The evaluation consists of region hierarchy--based image generation and cross-level similarity comparisons. We carry out an experiment by prompting DALL-E 2, a state-of-the-art T2I generation model capable of generating photorealistic images, to depict a forest. We select forest as an object class that displays regional variation and can be characterized using spatial statistics. For a region in the hierarchy, our experiment reveals the regional defaults implicit in DALL-E 2, along with their scale-dependent nature and spatial relationships. In addition, we discover that the implicit defaults do not necessarily correspond to the most widely forested regions in reality. Our findings underscore a need for further investigation into the geography of T2I generation and other forms of generative AI.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。