This paper strives to measure apparent skin color in computer vision, beyond a unidimensional scale on skin tone. In their seminal paper Gender Shades, Buolamwini and Gebru have shown how gender classification systems can be biased against women with darker skin tones. Subsequently, fairness researchers and practitioners have adopted the Fitzpatrick skin type classification as a common measure to assess skin color bias in computer vision systems. While effective, the Fitzpatrick scale only focuses on the skin tone ranging from light to dark. Towards a more comprehensive measure of skin color, we introduce the hue angle ranging from red to yellow. When applied to images, the hue dimension reveals additional biases related to skin color in both computer vision datasets and models. We then recommend multidimensional skin color scales, relying on both skin tone and hue, for fairness assessments.
Biases in large-scale image datasets are known to influence the performance of computer vision models as a function of geographic context. To investigate the limitations of standard Internet data collection methods in low- and middle-income countries, we analyze human-centric image geo-diversity on a massive scale using geotagged Flickr images associated with each nation in Africa. We report the quantity and content of available data with comparisons to population-matched nations in Europe as well as the distribution of data according to fine-grained intra-national wealth estimates. Temporal analyses are performed at two-year intervals to expose emerging data trends. Furthermore, we present findings for an ``othering'' phenomenon as evidenced by a substantial number of images from Africa being taken by non-local photographers. The results of our study suggest that further work is required to capture image data representative of African people and their environments and, ultimately, to improve the applicability of computer vision models in a global context.
Speech AI Technologies are largely trained on publicly available datasets or by the massive web-crawling of speech. In both cases, data acquisition focuses on minimizing collection effort, without necessarily taking the data subjects' protection or user needs into consideration. This results to models that are not robust when used on users who deviate from the dominant demographics in the training set, discriminating individuals having different dialects, accents, speaking styles, and disfluencies. In this talk, we use automatic speech recognition as a case study and examine the properties that ethical speech datasets should possess towards responsible AI applications. We showcase diversity issues, inclusion practices, and necessary considerations that can improve trained models, while facilitating model explainability and protecting users and data subjects. We argue for the legal & privacy protection of data subjects, targeted data sampling corresponding to user demographics & needs, appropriate meta data that ensure explainability & accountability in cases of model failure, and the sociotechnical \& situated model design. We hope this talk can inspire researchers \& practitioners to design and use more human-centric datasets in speech technologies and other domains, in ways that empower and respect users, while improving machine learning models' robustness and utility.
Few datasets contain self-identified sensitive attributes, inferring attributes risks introducing additional biases, and collecting attributes can carry legal risks. Besides, categorical labels can fail to reflect the continuous nature of human phenotypic diversity, making it difficult to compare the similarity between same-labeled faces. To address these issues, we present A View From Somewhere (AVFS) -- a dataset of 638,180 human judgments of face similarity. We demonstrate the utility of AVFS for learning a continuous, low-dimensional embedding space aligned with human perception. Our embedding space, induced under a novel conditional framework, not only enables the accurate prediction of face similarity, but also provides a human-interpretable decomposition of the dimensions used in the human-decision making process, and the importance distinct annotators place on each dimension. We additionally show the practicality of the dimensions for collecting continuous attributes, performing classification, and comparing dataset attribute disparities.
Human-centric image datasets are critical to the development of computer vision technologies. However, recent investigations have foregrounded significant ethical issues related to privacy and bias, which have resulted in the complete retraction, or modification, of several prominent datasets. Recent works have tried to reverse this trend, for example, by proposing analytical frameworks for ethically evaluating datasets, the standardization of dataset documentation and curation practices, privacy preservation methodologies, as well as tools for surfacing and mitigating representational biases. Little attention, however, has been paid to the realities of operationalizing ethical data collection. To fill this gap, we present a set of key ethical considerations and practical recommendations for collecting more ethically-minded human-centric image data. Our research directly addresses issues of privacy and bias by contributing to the research community best practices for ethical data collection, covering purpose, privacy and consent, as well as diversity. We motivate each consideration by drawing on lessons from current practices, dataset withdrawals and audits, and analytical ethical frameworks. Our research is intended to augment recent scholarship, representing an important step toward more responsible data curation practices.
Previous work has shown the potential of deep learning to predict renal obstruction using kidney ultrasound images. However, these image-based classifiers have been trained with the goal of single-visit inference in mind. We compare methods from video action recognition (i.e. convolutional pooling, LSTM, TSM) to adapt single-visit convolutional models to handle multiple visit inference. We demonstrate that incorporating images from a patient's past hospital visits provides only a small benefit for the prediction of obstructive hydronephrosis. Therefore, inclusion of prior ultrasounds is beneficial, but prediction based on the latest ultrasound is sufficient for patient risk stratification.
When using medical images for diagnosis, either by clinicians or artificial intelligence (AI) systems, it is important that the images are of high quality. When an image is of low quality, the medical exam that produced the image often needs to be redone. In telemedicine, a common problem is that the quality issue is only flagged once the patient has left the clinic, meaning they must return in order to have the exam redone. This can be especially difficult for people living in remote regions, who make up a substantial portion of the patients at Portal Telemedicina, a digital healthcare organization based in Brazil. In this paper, we report on ongoing work regarding (i) the development of an AI system for flagging and explaining low-quality medical images in real-time, (ii) an interview study to understand the explanation needs of stakeholders using the AI system at OurCompany, and, (iii) a longitudinal user study design to examine the effect of including explanations on the workflow of the technicians in our clinics. To the best of our knowledge, this would be the first longitudinal study on evaluating the effects of XAI methods on end-users -- stakeholders that use AI systems but do not have AI-specific expertise. We welcome feedback and suggestions on our experimental setup.
Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabilities are as yet poorly characterized. In order to inform future research, prepare for disruptive new model capabilities, and ameliorate socially harmful effects, it is vital that we understand the present and near-future capabilities and limitations of language models. To address this challenge, we introduce the Beyond the Imitation Game benchmark (BIG-bench). BIG-bench currently consists of 204 tasks, contributed by 442 authors across 132 institutions. Task topics are diverse, drawing problems from linguistics, childhood development, math, common-sense reasoning, biology, physics, social bias, software development, and beyond. BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models. We evaluate the behavior of OpenAI's GPT models, Google-internal dense transformer architectures, and Switch-style sparse transformers on BIG-bench, across model sizes spanning millions to hundreds of billions of parameters. In addition, a team of human expert raters performed all tasks in order to provide a strong baseline. Findings include: model performance and calibration both improve with scale, but are poor in absolute terms (and when compared with rater performance); performance is remarkably similar across model classes, though with benefits from sparsity; tasks that improve gradually and predictably commonly involve a large knowledge or memorization component, whereas tasks that exhibit "breakthrough" behavior at a critical scale often involve multiple steps or components, or brittle metrics; social bias typically increases with scale in settings with ambiguous context, but this can be improved with prompting.
Harms resulting from the development and deployment of facial processing technologies (FPT) have been met with increasing controversy. Several states and cities in the U.S. have banned the use of facial recognition by law enforcement and governments, but FPT are still being developed and used in a wide variety of contexts where they primarily are regulated by state biometric information privacy laws. Among these laws, the 2008 Illinois Biometric Information Privacy Act (BIPA) has generated a significant amount of litigation. Yet, with most BIPA lawsuits reaching settlements before there have been meaningful clarifications of relevant technical intricacies and legal definitions, there remains a great degree of uncertainty as to how exactly this law applies to FPT. What we have found through applications of BIPA in FPT litigation so far, however, points to potential disconnects between technical and legal communities. This paper analyzes what we know based on BIPA court proceedings and highlights these points of tension: areas where the technical operationalization of BIPA may create unintended and undesirable incentives for FPT development, as well as areas where BIPA litigation can bring to light the limitations of solely technical methods in achieving legal privacy values. These factors are relevant for (i) reasoning about biometric information privacy laws as a governing mechanism for FPT, (ii) assessing the potential harms of FPT, and (iii) providing incentives for the mitigation of these harms. By illuminating these considerations, we hope to empower courts and lawmakers to take a more nuanced approach to regulating FPT and developers to better understand privacy values in the current U.S. legal landscape.