Nearest neighbors (NN) are traditionally used to compute final decisions, e.g., in Support Vector Machines or k-NN classifiers, and to provide users with explanations for the model's decision. In this paper, we show a novel utility of nearest neighbors: To improve predictions of a frozen, pretrained classifier C. We leverage an image comparator S that (1) compares the input image with NN images from the top-K most probable classes; and (2) uses S's output scores to weight the confidence scores of C. Our method consistently improves fine-grained image classification accuracy on CUB-200, Cars-196, and Dogs-120. Also, a human study finds that showing lay users our probable-class nearest neighbors (PCNN) improves their decision accuracy over prior work which only shows only the top-1 class examples.

翻译：最近邻（NN）传统上用于计算最终决策（例如支持向量机或k-NN分类器），并向用户提供模型决策的解释。本文展示了最近邻的一种新用途：改进冻结的预训练分类器C的预测性能。我们利用图像比较器S，其功能包括：（1）将输入图像与来自前K个最可能类别的近邻图像进行比较；（2）利用S的输出得分对分类器C的置信度得分进行加权。本方法在CUB-200、Cars-196和Dogs-120数据集上持续提升了细粒度图像分类准确率。此外，一项人类研究表明，向非专业用户展示我们提出的"可能类别最近邻"（PCNN），相较于仅展示Top-1类别示例的先前工作，可显著提升其分类决策准确率。