arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2007.12248cs.LGcs.AIcs.CVcs.HCstat.ML
收藏

视觉效果有用吗?模型在环预测的实例研究

Are Visual Explanations Useful? A Case Study in Model-in-the-Loop Prediction

MIT Media Lab(麻省理工学院媒体实验室);MIT CSAIL(麻省理工学院计算机科学与人工智能实验室)

Eric Chu, Deb Roy, Jacob Andreas

摘要:

我们提出了一个随机对照试验的模型在循环回归任务,其目标是测量在何种程度上(1)模型预测的良好解释增加人类的准确性,(2)错误的解释降低人类对模型的信任。我们研究了基于图像的年龄预测任务中基于视觉显着性的解释,人类和学习模型各自都有能力,但不是非常熟练,而且经常不同意。我们的实验设计将模型质量与解释质量分开,并可以比较涉及不同质量水平的各种解释的治疗。我们发现,呈现模型预测可以提高人类的准确性。然而,各种视觉解释无法显著改变人类的准确性或对模型的信任-无论解释是否表征准确的模型,不准确的模型,还是随机生成并独立于输入图像。这些研究结果表明,需要更多的下游决策任务的解释,更好的设计为基础的工具,为用户提供解释,更好的方法来产生解释的评价。

英文摘要:

We present a randomized controlled trial for a model-in-the-loop regression task, with the goal of measuring the extent to which (1) good explanations of model predictions increase human accuracy, and (2) faulty explanations decrease human trust in the model. We study explanations based on visual saliency in an image-based age prediction task for which humans and learned models are individually capable but not highly proficient and frequently disagree. Our experimental design separates model quality from explanation quality, and makes it possible to compare treatments involving a variety of explanations of varying levels of quality. We find that presenting model predictions improves human accuracy. However, visual explanations of various kinds fail to significantly alter human accuracy or trust in the model - regardless of whether explanations characterize an accurate model, an inaccurate one, or are generated randomly and independently of the input image. These findings suggest the need for greater evaluation of explanations in downstream decision making tasks, better design-based tools for presenting explanations to users, and better approaches for generating explanations.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑