Ensemble Feature for Person Re-Identification
This work addresses the robustness issue in person re-identification for surveillance and security applications, but it is incremental as it builds on existing ResNet-50 architecture with ensemble techniques.
The paper tackled the problem of insufficient robustness in deep feature representation for person re-identification by proposing an ensemble network (EnsembleNet) that divides a single network into multiple branches and concatenates their features, achieving state-of-the-art performance on public benchmarks like Market1501, DukeMTMC-reID, and CUHK03.
In person re-identification (re-ID), the key task is feature representation, which is used to compute distance or similarity in prediction. Person re-ID achieves great improvement when deep learning methods are introduced to tackle this problem. The features extracted by convolutional neural networks (CNN) are more effective and discriminative than the hand-crafted features. However, deep feature extracted by a single CNN network is not robust enough in testing stage. To improve the ability of feature representation, we propose a new ensemble network (EnsembleNet) by dividing a single network into multiple end-to-end branches. The ensemble feature is obtained by concatenating each of the branch features to represent a person. EnsembleNet is designed based on ResNet-50 and its backbone shares most of the parameters for saving computation and memory cost. Experimental results show that our EnsembleNet achieves the state-of-the-art performance on the public Market1501, DukeMTMC-reID and CUHK03 person re-ID benchmarks.