Fast and Accurate Person Re-Identification with RMNet
This work addresses efficient person re-identification for embedded systems, offering a practical solution with incremental improvements in speed.
The authors tackled the problem of person re-identification by introducing RMNet, a neural network architecture optimized for embedded vision, which achieved top-3 state-of-the-art performance on the Market-1501 challenge while significantly outperforming others in inference speed.
In this paper we introduce a new neural network architecture designed to use in embedded vision applications. It merges the best working practices of network architectures like MobileNets and ResNets to our named RMNet architecture. We also focus on key moments of building mobile architectures to carry out in the limited computation budget. Additionally, to demonstrate the effectiveness of our architecture we evaluate the RMNet backbone on Person Re-identification task. The proposed approach is in top 3 of state of the art solutions on Market-1501 challenge, however our method significantly outperforms them by the inference speed.