In recent years, deep metric learning and its probabilistic extensions claimed state-of-the-art results in the face verification task. Despite improvements in face verification, probabilistic methods received little attention in the research community and practical applications. In this paper, we, for the first time, perform an in-depth analysis of known probabilistic methods in verification and retrieval tasks. We study different design choices and propose a simple extension, achieving new state-of-the-art results among probabilistic methods. Finally, we study confidence prediction and show that it correlates with data quality, but contains little information about prediction error probability. We thus provide a new confidence evaluation benchmark and establish a baseline for future confidence prediction research. PyTorch implementation is publicly released.
翻译:近些年来,深入的衡量学习及其概率扩展声称在面对面的核查任务中取得了最新的最新结果。尽管在面对面的核查方面有了改进,但概率方法在研究界和实际应用方面很少受到重视。在本文件中,我们首次对已知的核查和检索任务中的概率分析进行了深入分析。我们研究了不同的设计选择,提出了简单的扩展,在概率方法中取得了新的最新结果。最后,我们研究了信心预测,并表明它与数据质量相关,但几乎没有关于预测误差概率的信息。因此,我们提供了新的信心评估基准,并为未来信心预测研究确定了基准。PyTorrch的实施公开发布。