Hierarchical and Efficient Learning for Person Re-Identification
This addresses efficiency concerns for practical deployment of person re-identification systems, though it appears incremental in combining existing ideas.
The paper tackles the problem of balancing accuracy and efficiency in person re-identification by proposing HENet, which learns hierarchical features and uses Random Polygon Erasing for occlusion robustness, achieving competitive results on multiple datasets.
Recent works in the person re-identification task mainly focus on the model accuracy while ignore factors related to the efficiency, e.g. model size and latency, which are critical for practical application. In this paper, we propose a novel Hierarchical and Efficient Network (HENet) that learns hierarchical global, partial, and recovery features ensemble under the supervision of multiple loss combinations. To further improve the robustness against the irregular occlusion, we propose a new dataset augmentation approach, dubbed Random Polygon Erasing (RPE), to random erase irregular area of the input image for imitating the body part missing. We also propose an Efficiency Score (ES) metric to evaluate the model efficiency. Extensive experiments on Market1501, DukeMTMC-ReID, and CUHK03 datasets shows the efficiency and superiority of our approach compared with epoch-making methods.