论文标题
视觉解释有用吗？在循环预测中的案例研究
Are Visual Explanations Useful? A Case Study in Model-in-the-Loop Prediction
论文作者
论文摘要
我们提出了一个随机对照试验，用于模型中的回归任务，目的是衡量（1）模型预测的良好解释提高了人类准确性的程度，以及（2）错误的解释降低了模型中人类的信任。我们研究基于视觉显着性的解释，在基于图像的年龄预测任务中，人类和学识渊博的模型具有单独的能力，但不熟练且经常不同意。我们的实验设计将模型质量与解释质量区分开，并可以比较涉及各种质量水平的解释的治疗方法。我们发现提出模型预测提高了人类的准确性。但是，各种类型的视觉解释无法显着改变模型中的人类准确性或信任 - 无论解释是表征精确模型，不准确的模型还是随机和独立于输入图像而产生的。这些发现表明，需要对下游决策任务中的解释进行更好的评估，更好的基于设计的工具，用于向用户介绍解释，以及更好地生成解释的方法。
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.
