Besides providing insights into how an image classifier makes its predictions, nearest-neighbor examples also help humans make more accurate decisions. Yet, leveraging this type of explanation to improve both human-AI team accuracy and classifier's accuracy remains an open question. In this paper, we aim to increase both types of accuracy by (1) comparing the input image with post-hoc, nearest-neighbor explanations using a novel network (AdvisingNet), and (2) employing a new reranking algorithm. Over different baseline models, our method consistently improves the image classification accuracy on CUB-200 and Cars-196 datasets. Interestingly, we also reach the state-of-the-art human-AI team accuracy on CUB-200 where both humans and an AdvisingNet make decisions on complementary subsets of images.

翻译：除了为图像分类器的预测提供洞察外，最近邻示例还能帮助人类做出更准确的决策。然而，利用这类解释来同时提升人机协同准确率和分类器准确率仍是一个悬而未决的问题。本文旨在通过以下两种途径提升这两类准确率：(1) 使用新型网络（AdvisingNet）将输入图像与事后生成的最近邻解释进行对比；(2) 采用新的重排序算法。在多个基线模型上，我们的方法在CUB-200和Cars-196数据集上持续提升了图像分类准确率。值得注意的是，我们在CUB-200数据集上还达到了最先进的人机协同准确率——在该任务中，人类与AdvisingNet分别对互补的图像子集进行决策。