FAI: Towards Holistic Bias Mitigation in Computer Vision Systems

FAI：迈向计算机视觉系统中的整体偏差缓解

• 批准号: 2041009
• 负责人: Nuno Vasconcelos
• 金额: $ 37.5万
• 依托单位: University of California-San Diego
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-02-01 至 2024-01-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2041009&HistoricalAwards=false
• 关键词: FAI; Towards; Holistic; Bias; Mitigation

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.

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，例如雇用或解雇个人或监禁期限，人们越来越担心这些系统的公平性。需要保证人工智能系统不会对部分人群产生偏见。该项目旨在减轻计算机视觉领域的人工智能偏见，计算机视觉是一种被称为深度学习的流行人工智能形式的最新进展的推动应用。计算机视觉系统在从医疗保健到执法等社会领域越来越普遍：从分析皮肤图片以检测黑色素瘤的应用程序到刑事调查中使用的人脸识别系统。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。有偏见的数据源于不良的图像收集实践，通常是某些人群的代表性不足。带有偏见的注释是由于使用带有未经训练的图像标记者的注释平台而产生的，这些标记者倾向于生成反映自己的图像解释的注释，而不是客观的标签。有偏差的模型可能是由于用于训练模型的数据集上数据或注释偏差的存在，或者有偏差的模型架构的选择而产生的。 这三个偏差组成部分在文献中受到了不同的关注，之前的大多数工作都集中在模型偏差的缓解上。然而，这通常归结为淡化拥有大量数据的群体并提升数据稀缺的群体。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种新框架来在一个统一的偏差缓解架构中共同解决三个偏差来源，从而克服这一问题。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）数据集偏差缓解算法，用于识别和降低偏差示例的权重，并在大量数据池中寻找其他示例以抵消相关偏差。 2）基于机器教学算法的标签偏差缓解系统，该算法建立清晰、可复制和可审核的程序，教注释者如何在没有标签偏差的情况下标记图像。 3）基于反事实视觉解释的模型审计技术，可以可视化影响模型决策的因素以及它们为何存在偏见。这三个模块组合成一个架构，通过数据集、注释器和模型的迭代优化来最小化偏差，从而减轻联合数据集、标签和模型偏差。该项目将生成用于数据集偏差缓解、无偏差注释器培训、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。这将得到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消除偏见的工具的补充。还计划开展多项活动，以扩大代表性不足的 K-12 和本科生在 STEM 领域的参与。它们将包括从加州大学圣地亚哥分校项目中招募的此类学生团队的参与，这些项目旨在增加这些群体对 STEM 的参与，并旨在让这些学生尽早接触现实世界工程、公平机器学习和深度学习系统的挑战。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Towards Professional Level Crowd Annotation of Expert Domain Data

• DOI: 10.1109/cvpr52729.2023.00309
• 发表时间: 2023-06
• 期刊: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
• 作者: Pei Wang;N. Vasconcelos

SCOUT: Self-Aware Discriminant Counterfactual Explanations

• DOI: 10.1109/cvpr42600.2020.00900
• 发表时间: 2020-04
• 期刊: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
• 作者: Pei Wang;N. Vasconcelos

VALHALLA: Visual Hallucination for Machine Translation

• DOI: 10.1109/cvpr52688.2022.00515
• 发表时间: 2022-05
• 期刊: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
• 作者: Yi Li-;Rameswar Panda;Yoon Kim;Chun-Fu Chen;R. Feris;David Cox;N. Vasconcelos

Toward Unsupervised Realistic Visual Question Answering

走向无监督的现实视觉问答

• 发表时间: 2023
• 期刊: IEEE/CVF International Conference on Computer Vision
• 作者: Ho, Chih-Hui;Zhang, Yuwei;Vasconcelos, Nuno
• 通讯作者: Vasconcelos, Nuno

Improving Video Model Transfer with Dynamic Representation Learning

通过动态表示学习改进视频模型传输

• 发表时间: 2022
• 期刊: IEEE/CVF Conference on Computer Vision and Pattern Recognition
• 作者: Yi Li, Nuno Vasconcelos