Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification
This work addresses the problem of improving person re-identification accuracy for computer vision applications, representing an incremental advancement in metric learning methods.
The paper tackles person re-identification by proposing a new metric learning loss called margin sample mining loss (MSML) that incorporates hard sample mining, achieving better accuracy than methods like triplet loss and outperforming most state-of-the-art algorithms on datasets such as Market1501, MARS, CUHK03, and CUHK-SYSU.
Person re-identification (ReID) is an important task in computer vision. Recently, deep learning with a metric learning loss has become a common framework for ReID. In this paper, we also propose a new metric learning loss with hard sample mining called margin smaple mining loss (MSML) which can achieve better accuracy compared with other metric learning losses, such as triplet loss. In experi- ments, our proposed methods outperforms most of the state-of-the-art algorithms on Market1501, MARS, CUHK03 and CUHK-SYSU.