In Defense of the Triplet Loss for Person Re-Identification
In Defense of the Triplet Loss for Person Re-Identification
复制标题
DOI：
--
复制
发表时间：
2017-03
期刊：
影响因子：
--
通讯作者：
Alexander Hermans;Lucas Beyer;B. Leibe
中科院分区：
文献类型：
--
作者：
Alexander Hermans;Lucas Beyer;B. Leibe
在过去的几年里，计算机视觉领域经历了一场革命，主要是由于大型数据集的出现和深度卷积神经网络用于端到端学习。人员重新识别子字段也不例外。不幸的是，社区中流行的观点似乎是三重损失不如使用替代损失（分类，验证），然后是单独的度量学习步骤。我们表明，对于从头开始训练的模型以及预训练的模型，使用三重丢失的变体来执行端到端深度度量学习的性能远远优于大多数其他已发表的方法。
In the past few years, the field of computer vision has gone through a revolution fueled mainly by the advent of large datasets and the adoption of deep convolutional neural networks for end-to-end learning. The person re-identification subfield is no exception to this. Unfortunately, a prevailing belief in the community seems to be that the triplet loss is inferior to using surrogate losses (classification, verification) followed by a separate metric learning step. We show that, for models trained from scratch as well as pretrained ones, using a variant of the triplet loss to perform end-to-end deep metric learning outperforms most other published methods by a large margin.