We identify "values" as actions that classifiers take that speak to open questions of significant social concern. Investigating a classifier's values builds on studies of social bias that uncover how classifiers participate in social processes beyond their creators' forethought. In our case, this participation involves what counts as nutritious, what it means to be modest, and more. Unlike AI social bias, however, a classifier's values are not necessarily morally loathsome. Attending to image classifiers' values can facilitate public debate and introspection about the future of society. To substantiate these claims, we report on an extensive examination of both ImageNet training/validation data and ImageNet-trained classifiers with custom testing data. We identify perceptual decision boundaries in 118 categories that address open questions in society, and through quantitative testing of rival datasets we find that ImageNet-trained classifiers enact at least 7 values through their perceptual decisions. To contextualize these results, we develop a conceptual framework that integrates values, social bias, and accuracy, and we describe a rhetorical method for identifying how context affects the values that a classifier enacts. We also discover that classifier performance does not straightforwardly reflect the proportions of subgroups in a training set. Our findings bring a rich sense of the social world to ML researchers that can be applied to other domains beyond computer vision.

翻译：我们识别出分类器在涉及重大社会关注的未决问题上所采取的行动为“价值观”。探究分类器的价值观，是对揭示分类器如何超越设计者预期而参与社会过程的社会偏见研究的深化。在我们的案例中，这种参与涉及“何为营养”、“何为谦逊”等问题。然而，与人工智能的社会偏见不同，分类器的价值观未必是道德上令人憎恶的。关注图像分类器的价值观可以促进关于社会未来的公共辩论与反思。为证实这些主张，我们报告了对ImageNet训练/验证数据以及经自定义测试数据测试的ImageNet训练分类器的广泛研究。我们识别出118个类别的感知决策边界，这些边界回应了社会中的未决问题；通过对比数据集的定量测试，我们发现ImageNet训练的分类器通过其感知决策至少执行了7种价值观。为将这些结果置于背景中，我们构建了一个整合价值观、社会偏见与准确性的概念框架，并描述了一种识别语境如何影响分类器所执行价值观的修辞方法。我们还发现，分类器的性能并不直接反映训练集中子群体的比例。我们的研究结果为机器学习研究者带来了对社会世界丰富的理解，且可应用于计算机视觉之外的领域。