Compact Network Training for Person ReID
This work addresses the need for practical, lightweight models in person ReID, which is incremental as it builds on existing methods but focuses on reducing model size and improving deployability.
The authors tackled the problem of person re-identification (ReID) by developing a compact network and training regime, achieving state-of-the-art results on Market1501 and DukeMTMC datasets and demonstrating cross-task applicability with SotA performance in multi-object tracking.
The task of person re-identification (ReID) has attracted growing attention in recent years leading to improved performance, albeit with little focus on real-world applications. Most SotA methods are based on heavy pre-trained models, e.g. ResNet50 (~25M parameters), which makes them less practical and more tedious to explore architecture modifications. In this study, we focus on a small-sized randomly initialized model that enables us to easily introduce architecture and training modifications suitable for person ReID. The outcomes of our study are a compact network and a fitting training regime. We show the robustness of the network by outperforming the SotA on both Market1501 and DukeMTMC. Furthermore, we show the representation power of our ReID network via SotA results on a different task of multi-object tracking.