Uncovering Regional Defaults from Photorealistic Forests in Text-to-Image Generation with DALL-E 2
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Image GenerationText to Image GenerationText-to-Image GenerationSimilar Papers 제목 키워드 기반
A regional model for estimating the aboveground carbon density of Borneo's tropical forests from airborne laser scanning
Borneo contains some of the world's most biodiverse and carbon dense tropical forest, but this 750,000-km2 island has lost 62% of its old-growth forests within the last 40 years. Efforts to protect and restore the remain…
ForestSim: A Synthetic Benchmark for Intelligent Vehicle Perception in Unstructured Forest Environments
Robust scene understanding is essential for intelligent vehicles operating in natural, unstructured environments. While semantic segmentation datasets for structured urban driving are abundant, the datasets for extremely…
Semantic SegmentationScene UnderstandingDefault Machine Learning Hyperparameters Do Not Provide Informative Initialization for Bayesian Optimization
Bayesian Optimization (BO) is a standard tool for hyperparameter tuning thanks to its sample efficiency on expensive black-box functions. While most BO pipelines begin with uniform random initialization, default hyperpar…
Visual Appearance Analysis of Forest Scenes for Monocular SLAM
Monocular simultaneous localisation and mapping (SLAM) is a cheap and energy efficient way to enable Unmanned Aerial Vehicles (UAVs) to safely navigate managed forests and gather data crucial for monitoring tree health. …
NavigateCredit card score prediction using machine learning models: A new dataset
The use of credit cards has recently increased, creating an essential need for credit card assessment methods to minimize potential risks. This study investigates the utilization of machine learning (ML) models for credi…
feature selectionregression