Image outlier detection (OD) is an essential tool to ensure the quality and accuracy of image datasets used in computer vision tasks. Most existing approaches, however, require a set of in-distribution data for training prior to outlier prediction. The quality and quantity of the data can influence the resulting performance. Thus, selecting a suitable in-distribution set often requires considerable effort. In this work, we propose RANSAC-NN, an unsupervised image OD algorithm designed to detect outliers within contaminated sets in a one-class classification fashion. Without any training, RANSAC-NN performs favorably in comparison to other well-established methods in a variety of OD benchmarks. Furthermore, we show that our method can enhance the robustness of existing OD methods by simply applying RANSAC-NN during pre-processing.

翻译：图像离群点检测是确保计算机视觉任务中图像数据集质量与准确性的关键工具。然而，现有方法大多需要在离群点预测前使用一组分布内数据进行训练，且数据质量与数量会直接影响检测性能，因此选择合适的分布内数据集往往需要大量人工投入。本文提出RANSAC-NN——一种无监督图像离群点检测算法，通过单类分类框架实现受污染数据集中的离群点识别。该方法无需任何训练，在多种离群点检测基准测试中均展现出优于其他成熟方法的性能。此外，实验表明，仅需在预处理阶段应用RANSAC-NN即可增强现有离群点检测方法的鲁棒性。