论文标题
通过公制学习建立计算高效且普通的人重新识别模型
Building Computationally Efficient and Well-Generalizing Person Re-Identification Models with Metric Learning
论文作者
论文摘要
这项工作考虑了域转移重新识别的问题。在一个数据集中接受培训的培训，重新识别模型通常在看不见的数据上表现较差。部分原因是，此差距是由相对较小的人重新识别数据集（例如，与面部识别数据集相比）引起的，但它也与培训目标有关。我们建议使用公制学习目标，即Am-Softmax损失，以及一些其他培训实践来建立良好的计算高效模型。我们使用最近提出的Omni级网络（OSNET）体系结构，结合了几种培训技巧和体系结构调整，以在三个设置中的大规模MSMT17数据集中获得跨域泛化问题的最先进结果：MSMT17-ALL-> DUKEMTMC，MSMT17-TRAIN-> TRAIN-> MATCHIN-MATCH11550117-ALL-MACKEN1117-- ALL-> DUKEMTMC，ALL-> DUKEMTMC。
This work considers the problem of domain shift in person re-identification.Being trained on one dataset, a re-identification model usually performs much worse on unseen data. Partially this gap is caused by the relatively small scale of person re-identification datasets (compared to face recognition ones, for instance), but it is also related to training objectives. We propose to use the metric learning objective, namely AM-Softmax loss, and some additional training practices to build well-generalizing, yet, computationally efficient models. We use recently proposed Omni-Scale Network (OSNet) architecture combined with several training tricks and architecture adjustments to obtain state-of-the art results in cross-domain generalization problem on a large-scale MSMT17 dataset in three setups: MSMT17-all->DukeMTMC, MSMT17-train->Market1501 and MSMT17-all->Market1501.
