FAI: Measuring and Mitigating Biases in Generic Image Representations

FAI：测量和减轻通用图像表示中的偏差

• 批准号: 2040961
• 负责人: Vicente Ordonez
• 金额: $ 37.5万
• 依托单位: University of Virginia Main Campus
• 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 2022-04-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2040961&HistoricalAwards=false
• 关键词: FAI; Measuring; Mitigating; Biases; Generic

Visual recognition is a remarkable task performed by the human brain. Computational methods trained to emulate this capability rely on observing millions of examples of visual input paired with human annotations. These computational methods have made great progress and are being increasingly adopted in many user-facing applications such as image search, automated image tagging, semi-autonomous navigation systems, smart virtual assistants, etc. However, the underlying visual recognition models in these systems often produce errors by associating sensitive variables of societal significance with their predictions. The goal of this project is to measure and mitigate such errors in a systematic fashion. For example, if a method is able to recognize images of scenes such as 'classroom', the goal of this project is to ensure that such predictions are obtained based on cues such as the presence of a whiteboard, chairs, desks, and other elements typically needed for a space to function as a classroom and not based on incidental elements such as the characteristics or attributes of people present in the classroom. To this end, this project aims to make it easier to determine to what extent methods for computational visual recognition rely on spurious associations with incidental elements.This project will provide a study of societal biases present in current methods and models for computational visual recognition that are widely used as a source of generic visual representations. The developed methods will be based on solid foundations drawn from both the machine learning, computer vision, and software testing communities. The project introduces association tests to probe models trained under a variety of conditions to systematically disentangle the biases introduced during generic visual representation learning. The project will be 1) developing a general assessment methodology to measure various types of biases in generic visual representation learning, 2) proposing methods to diminish the impact of these biases in existing generic visual representation extraction models, and 3) measuring the impact of these biases on some key downstream tasks. These three research aims will be complemented by a comprehensive evaluation plan and broadening participation activities. This research effort will bring novel insights into the sources of biases in the predictions of computer vision models and methodologies to make informed decisions about the risks in the deployment of such models.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.

视觉识别是人脑执行的一项出色的任务。经过训练以模仿这种能力的计算方法取决于观察数百万的视觉输入示例与人类注释。这些计算方法已经取得了长足的进步，并且在许多面向用户的应用程序中越来越多地采用，例如图像搜索，自动化图像标记，半自主导航系统，智能虚拟助手等。但是，这些系统中的基本视觉识别模型通常通过与他们的预测相关联的社会敏感变量来通过将敏感变量关联而产生错误。该项目的目的是以系统的方式衡量和减轻此类错误。例如，如果一种方法能够识别诸如“教室”之类的场景的图像，那么该项目的目的是确保基于诸如存在的暗示，例如存在白板，椅子，书桌和其他元素，通常需要一个空间作为教室，而不是基于偶然的元素，例如在教室中存在的特征或属性。为此，该项目旨在使确定计算视觉识别的方法在多大程度上取决于与附带元素的虚假关联。该项目将提供对当前方法和模型中的社会偏见的研究，用于计算视觉识别，这些方法被广泛用作通用视觉表示的来源。开发的方法将基于从机器学习，计算机视觉和软件测试社区中得出的坚实基础。该项目将关联测试引入了在各种条件下训练的探测模型，以系统地解开通用视觉表示学习过程中引入的偏见。该项目将是1）开发一种一般评估方法，以测量通用视觉表示学习中各种类型的偏见，2）提出方法来减少这些偏见在现有的通用视觉表示提取模型中的影响，以及3）测量这些偏见对某些关键任务的影响。这三个研究目标将由全面的评估计划和扩大参与活动提供补充。这项研究的工作将在计算机视觉模型和方法论的预测中为偏见的来源带来新的见解，以做出有关部署此类模型的风险的明智决定。该奖项反映了NSF的法定任务，并被视为值得通过基金会的知识分子和更广泛影响的评估来通过评估来获得支持。

项目成果

Evolving Image Compositions for Feature Representation Learning

• 发表时间: 2021-06
• 作者: Paola Cascante-Bonilla;Arshdeep Sekhon;Yanjun Qi;Vicente Ordonez

Towards Learning (Dis)-Similarity of Source Code from Program Contrasts

• DOI: 10.18653/v1/2022.acl-long.436
• 发表时间: 2021-10
• 作者: Yangruibo Ding;Luca Buratti;Saurabh Pujar;Alessandro Morari;Baishakhi Ray;Saikat Chakraborty

Sim VQA: Exploring Simulated Environments for Visual Question Answering

• DOI: 10.1109/cvpr52688.2022.00500
• 发表时间: 2022-03
• 期刊: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
• 作者: Paola Cascante-Bonilla;Hui Wu;Letao Wang;R. Feris;Vicente Ordonez