REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets
REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets
复制标题
DOI：
10.1007/s11263-022-01625-5
复制
发表时间：
2020-04
影响因子：
19.5
通讯作者：
Angelina Wang;Alexander Liu;Ryan Zhang;Anat Kleiman;Leslie Kim;Dora Zhao;Iroha Shirai;Arvind Narayanan;Olga Russakovsky
中科院分区：
文献类型：
--
作者：
Angelina Wang;Alexander Liu;Ryan Zhang;Anat Kleiman;Leslie Kim;Dora Zhao;Iroha Shirai;Arvind Narayanan;Olga Russakovsky
众所周知，机器学习模型会延续甚至放大数据中存在的偏见。然而，这些数据偏差通常在部署模型之后才会变得明显。我们的工作解决了这个问题，并使大规模数据集的抢先分析成为可能。揭示视觉偏差（revision）是一个帮助调查视觉数据集的工具，可以在三个维度上显示潜在的偏差：(1)基于对象的，(2)基于人的，(3)基于地理的。基于对象的偏差与所描绘对象的大小、背景或多样性有关。基于人的指标侧重于分析数据集中的人的写照。基于地理的分析考虑不同地理位置的表示。这三个维度深深地交织在一起，它们是如何相互作用来影响数据集的，而《修正》揭示了这一点；用户有责任考虑文化和历史背景，并确定哪些揭示的偏见可能是有问题的。该工具通过建议可采取的可操作步骤来进一步帮助用户减轻所显示的偏见。总的来说，我们工作的关键目标是在管道的早期解决机器学习偏差问题。修订可在https://github.com/princetonvisualai/revise-tool。
Machine learning models are known to perpetuate and even amplify the biases present in the data. However, these data biases frequently do not become apparent until after the models are deployed. Our work tackles this issue and enables the preemptive analysis of large-scale datasets. REvealing VIsual biaSEs (REVISE) is a tool that assists in the investigation of a visual dataset, surfacing potential biases along three dimensions: (1) object-based, (2) person-based, and (3) geography-based. Object-based biases relate to the size, context, or diversity of the depicted objects. Person-based metrics focus on analyzing the portrayal of people within the dataset. Geography-based analyses consider the representation of different geographic locations. These three dimensions are deeply intertwined in how they interact to bias a dataset, and REVISE sheds light on this; the responsibility then lies with the user to consider the cultural and historical context, and to determine which of the revealed biases may be problematic. The tool further assists the user by suggesting actionable steps that may be taken to mitigate the revealed biases. Overall, the key aim of our work is to tackle the machine learning bias problem early in the pipeline. REVISE is available at https://github.com/princetonvisualai/revise-tool.