FAI: Towards Holistic Bias Mitigation in Computer Vision Systems

随着人工智能（AI）系统在改变生活的决策中的使用越来越多，例如雇佣或解雇个人或刑期长短，人们越来越关注这些系统的公平性。有必要保证人工智能系统不会对部分人口有偏见。该项目旨在减轻计算机视觉领域的AI偏见，这是一种被称为深度学习的流行AI形式的最新进展的驱动应用。计算机视觉系统在从医疗保健到执法的社会领域越来越普遍：从分析黑色素瘤检测皮肤图片的应用程序到用于刑事调查的人脸识别系统。这些系统受到三个主要偏差来源的影响：有偏差的数据，有偏差的注释和有偏差的模型。有偏见的数据来自不良的图像收集做法，通常是某些人口群体的代表性不足。有偏见的注释来自于使用未经训练的图像标注者的注释平台，这些标注者倾向于生成反映他们自己的图像解释的注释，而不是客观标签。有偏模型可能源于用于训练模型的数据集上存在数据或注释偏差，或者选择有偏模型架构。 这三个偏差分量在文献中得到了不同的关注，大多数以前的工作集中在减轻模型偏差。然而，这通常归结为淡化有大量数据的群体，促进数据稀缺的群体。这种做法可能会损害整体系统性能。其余的偏差来源，数据集和注释，很少受到算法的关注。该项目旨在通过引入一个新的框架来克服这个问题，以在一个统一的偏差缓解架构中共同解决三个偏差来源。该架构旨在通过三个不同模块的迭代优化来训练公平分类器：1）数据集偏见缓解算法，该算法识别和降低偏见示例的权重，并在大型数据池中寻找额外的示例以抵消相关的偏见。2)基于机器教学算法的标签偏见缓解系统，建立清晰，可复制和可审计的程序，以教注释者如何在没有标签偏见的情况下标记图像。3)基于反事实视觉解释的模型审计技术，使有助于模型决策的因素以及它们为什么有偏见的可视化。这三个模块联合收割机组成一个架构，通过迭代优化数据集、注释器和模型来减少数据集、标签和模型的偏差，从而最大限度地减少偏差。该项目将生成用于数据集偏倚缓解、无偏倚注释者培训、解释和可视化、模型审计和公平模型培训的软件，这些软件将在研究者网站上提供。这将与用于设计各种形式的偏见缓解算法的数据集以及帮助从业者检测和对抗偏见的工具相补充。还计划开展一些活动，以扩大代表性不足的K-12和本科生在STEM领域的参与。他们将包括一个这样的学生团队的参与，从加州圣地亚哥大学的计划，旨在增加这些群体在干的参与，并旨在为这些学生提供早期接触现实世界的挑战工程，公平的机器学习，该奖项反映了NSF的法定使命，并通过使用基金会的知识产权进行评估，优点和更广泛的影响审查标准。

With the increasing use of artificial intelligence (AI) systems in life-changing decisions, such as hiring or firing of individuals or the length of jail sentences, there has been an increasing concern about the fairness of these systems. There is a need to guarantee that AI systems are not biased against segments of the population. This project aims to mitigate AI bias in the domain of computer vision, a driving application for much of the recent advances in a popular form of AI known as deep learning. Computer vision systems are increasingly prevalent in areas of society ranging from healthcare to law enforcement: from apps that analyze skin pictures for melanoma detection to face recognition systems used in criminal investigations. These systems are subject to three major sources of bias: biased data, biased annotations, and biased models. Biased data follows from poor image collection practices, typically the under-representation of certain population groups. Biased annotation follows from the use of annotation platforms with untrained image labelers, who tend to produce annotations that reflect their own image interpretations, rather than objective labels. Biased models can ensue from either the existence of data or annotation biases on the datasets used to train the models, or the choice of biased model architectures. The three bias components have received different attention in the literature, with most previous work focusing on the mitigation of model bias. However, this usually boils down to downplaying groups for which there is a lot of data and promoting groups for which data is scarce. This practice can hurt overall system performance. The remaining sources of bias, datasets and annotation, have received very little algorithmic attention. The project aims to overcome this problem, by introducing a new framework to jointly address the three sources of bias within one unified bias mitigation architecture. This architecture aims to train fair classifiers by iterative optimization of three distinct modules: 1) Dataset bias mitigation algorithms that identify and downweigh biased examples and seek additional examples in a large pool of data to counterbalance the associated biases. 2) Label bias mitigation systems based on machine teaching algorithms that establish clear, replicable, and auditable procedures to teach annotators how to label images without label bias. 3) Model auditing techniques based on counterfactual visual explanations that enable the visualization of the factors contributing to model decisions and why they are biased. The three modules combine into an architecture for joint dataset, label, and model bias mitigation by iterative optimization of datasets, annotators, and models to minimize bias. The project will generate software for dataset bias mitigation, unbiased annotator training, explanations and visualizations, model auditing, and fair model training, which will be made available from the investigator website. This will be complemented with datasets for the design of various form of bias mitigation algorithms, and tools to help practitioners detect and combat bias. Several activities are also planned to broaden the participation of underrepresented K-12 and undergraduate students in the STEM field. They will include the participation of a team of such students, recruited from University of California San Diego programs that aim to increase the participation of these groups in STEM, and aim to provide these students with early exposure to the challenges of real-world engineering, fair machine learning, and deep learning systems.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.