开源框架统一评测视觉偏见缓解方法，提升可复现性。
VB-Mitigator: An Open-source Framework for Evaluating and Advancing Visual Bias Mitigation
- 提供12种主流缓解方法与7个基准数据集的统一实现
- 支持新方法、数据集、指标的无缝扩展
- 适合公平性研究者快速对比和验证新算法
计算机视觉模型中的偏见仍是重大挑战，常导致不公平、不可靠且泛化能力差的AI系统。尽管偏见缓解研究日益增多，但零散的实现方式和不一致的评估标准仍阻碍进展。不同研究使用各异的数据集和度量指标，难以复现和公平比较。为此，我们提出开源框架VB-Mitigator，旨在统一视觉偏见缓解技术的研发与评估流程。该框架集成12种成熟缓解方法与7个多样化基准数据集，具备良好可扩展性，支持新增方法、数据集、度量指标和模型。同时，我们推荐最佳评估实践，并提供前沿方法的全面性能对比，助力构建更公平的计算机视觉模型。
原文摘要 · Abstract (English)
Bias in computer vision models remains a significant challenge, often resulting in unfair, unreliable, and non-generalizable AI systems. Although research into bias mitigation has intensified, progress continues to be hindered by fragmented implementations and inconsistent evaluation practices. Disparate datasets and metrics used across studies complicate reproducibility, making it difficult to fairly assess and compare the effectiveness of various approaches. To overcome these limitations, we introduce the Visual Bias Mitigator (VB-Mitigator), an open-source framework designed to streamline the development, evaluation, and comparative analysis of visual bias mitigation techniques. VB-Mitigator offers a unified research environment encompassing 12 established mitigation methods, 7 diverse benchmark datasets. A key strength of VB-Mitigator is its extensibility, allowing for seamless integration of additional methods, datasets, metrics, and models. VB-Mitigator aims to accelerate research toward fairness-aware computer vision models by serving as a foundational codebase for the research community to develop and assess their approaches. To this end, we also recommend best evaluation practices and provide a comprehensive performance comparison among state-of-the-art methodologies.
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。