paper-with-me

Papers

Decomposed evaluations of geographic disparities in text-to-image models

2024-06-17 · Abhishek Sureddy, Dishant Padalia, Nandhinee Periyakaruppa, Oindrila Saha, Adina Williams, Adriana Romero-Soriano, Megan Richards, Polina Kirichenko, Melissa Hall

Recent work has identified substantial disparities in generated images of different geographic regions, including stereotypical depictions of everyday objects like houses and cars. However, existing measures for these disparities have been limited to either human evaluations, which are time-consuming and costly, or automatic metrics evaluating full images, which are unable to attribute these disparities to specific parts of the generated images. In this work, we introduce a new set of metrics, Decomposed Indicators of Disparities in Image Generation (Decomposed-DIG), that allows us to separately measure geographic disparities in the depiction of objects and backgrounds in generated images. Using Decomposed-DIG, we audit a widely used latent diffusion model and find that generated images depict objects with better realism than backgrounds and that backgrounds in generated images tend to contain larger regional disparities than objects. We use Decomposed-DIG to pinpoint specific examples of disparities, such as stereotypical background generation in Africa, struggling to generate modern vehicles in Africa, and unrealistically placing some objects in outdoor settings. Informed by our metric, we use a new prompting structure that enables a 52% worst-region improvement and a 20% average improvement in generated background diversity.

📄 PDF Abstract BibTeX arXiv:2406.11988

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeDiversityImage Generation

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
Latent Diffusion Model Diffusion models applied to latent spaces, which are normally built with (Variational) Autoencoders.

Similar Papers 제목 키워드 기반

DIG In: Evaluating Disparities in Image Generations with Indicators for Geographic Diversity

2023-08-11 · Melissa Hall, Candace Ross, Adina Williams, Nicolas Carion 외

The unprecedented photorealistic results achieved by recent text-to-image generative systems and their increasing use as plug-and-play content creation solutions make it crucial to understand their potential biases. In t…

BenchmarkingDiversityImage Generation

Mitigating Urban-Rural Disparities in Contrastive Representation Learning with Satellite Imagery

2022-11-16 · Miao Zhang, Rumi Chunara

Satellite imagery is being leveraged for many societally critical tasks across climate, economics, and public health. Yet, because of heterogeneity in landscapes (e.g. how a road looks in different places), models can sh…

AttributeContrastive LearningFairnessImage Segmentation+3

Does Progress On Object Recognition Benchmarks Improve Real-World Generalization?

2023-07-24 · Megan Richards, Polina Kirichenko, Diane Bouchacourt, Mark Ibrahim

For more than a decade, researchers have measured progress in object recognition on ImageNet-based generalization benchmarks such as ImageNet-A, -C, and -R. Recent advances in foundation models, trained on orders of magn…

Object Recognition

Measuring Geographic Performance Disparities of Offensive Language Classifiers

2022-09-15 · COLING 2022 10 · Brandon Lwowski, Paul Rad, Anthony Rios

Text classifiers are applied at scale in the form of one-size-fits-all solutions. Nevertheless, many studies show that classifiers are biased regarding different languages and dialects. When measuring and discovering the…

Contextual Budget Bandit for Food Rescue Volunteer Engagement

2025-09-13 · Ariana Tang, Naveen Raman, Fei Fang, Zheyuan Ryan Shi arxiv

Volunteer-based food rescue platforms tackle food waste by matching surplus food to communities in need. These platforms face the dual problem of maintaining volunteer engagement and maximizing the food rescued. Existing…

Multi-Armed Bandits