paper-with-me

홈 › Papers

Benchmarking the Fairness of Image Upsampling Methods

2024-01-24 · Mike Laszkiewicz, Imant Daunhawer, Julia E. Vogt, Asja Fischer, Johannes Lederer

Recent years have witnessed a rapid development of deep generative models for creating synthetic media, such as images and videos. While the practical applications of these models in everyday tasks are enticing, it is crucial to assess the inherent risks regarding their fairness. In this work, we introduce a comprehensive framework for benchmarking the performance and fairness of conditional generative models. We develop a set of metrics$\unicode{x2013}$inspired by their supervised fairness counterparts$\unicode{x2013}$to evaluate the models on their fairness and diversity. Focusing on the specific application of image upsampling, we create a benchmark covering a wide variety of modern upsampling methods. As part of the benchmark, we introduce UnfairFace, a subset of FairFace that replicates the racial distribution of common large-scale face datasets. Our empirical study highlights the importance of using an unbiased training set and reveals variations in how the algorithms respond to dataset imbalances. Alarmingly, we find that none of the considered methods produces statistically fair and diverse results. All experiments can be reproduced using our provided repository.

📄 PDF Abstract BibTeX arXiv:2401.13555

Code (1)

mikelasz/benchmarking-fairness-imageupsampling 공식 구현 pytorch

Tasks

BenchmarkingDiversityFairness

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Benchmarking Feature Upsampling Methods for Vision Foundation Models using Interactive Segmentation

2025-05-04 · Volodymyr Havrylov, Haiwen Huang, Dan Zhang, Andreas Geiger

Vision Foundation Models (VFMs) are large-scale, pre-trained models that serve as general-purpose backbones for various computer vision tasks. As VFMs' popularity grows, there is an increasing interest in understanding t…

BenchmarkingFeature UpsamplingInteractive SegmentationScene Understanding

FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methods

2023-06-15 · Xiaotian Han, Jianfeng Chi, Yu Chen, Qifan Wang 외

This paper introduces the Fair Fairness Benchmark (\textsf{FFB}), a benchmarking framework for in-processing group fairness methods. Ensuring fairness in machine learning is important for ethical compliance. However, the…

BenchmarkingFairnessGPU

FairX: A comprehensive benchmarking tool for model analysis using fairness, utility, and explainability

2024-06-20 · Md Fahim Sikder, Resmi Ramachandranpillai, Daniel de Leng, Fredrik Heintz

We present FairX, an open-source Python-based benchmarking tool designed for the comprehensive analysis of models under the umbrella of fairness, utility, and eXplainability (XAI). FairX enables users to train benchmarki…

BenchmarkingFairness

A Framework for Benchmarking Fairness-Utility Trade-offs in Text-to-Image Models via Pareto Frontiers

2025-08-22 · Marco N. Bochernitsan, Rodrigo C. Barros, Lucas S. Kupssinskü arxiv

Achieving fairness in text-to-image generation demands mitigating social biases without compromising visual fidelity, a challenge critical to responsible AI. Current fairness evaluation procedures for text-to-image model…

Text-to-Image Generation

Revisiting Pre-processing Group Fairness: A Modular Benchmarking Framework

2025-08-21 · Brodie Oldfield, Ziqi Xu, Sevvandi Kandanaarachchi arxiv

As machine learning systems become increasingly integrated into high-stakes decision-making processes, ensuring fairness in algorithmic outcomes has become a critical concern. Methods to mitigate bias typically fall into…