Ensemble Feature For Person Re-identification

Abstract

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 C

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywang2019ensemble

Related papers

• Adaptive Re-ranking Of Deep Feature For Person Re-identification (2018)0.00
• Deep-person: Learning Discriminative Deep Features For Person Re-identification (2017)16.90
• Triplet-based Deep Similarity Learning For Person Re-identification (2018)10.61
• A Discriminatively Learned CNN Embedding For Person Re-identification (2016)20.32
• Graph Convolution For Re-ranking In Person Re-identification (2021)8.35
• Auto-reid: Searching For A Part-aware Convnet For Person Re-identification (2019)17.27
• Fully Unsupervised Person Re-identification Viaselective Contrastive Learning (2020)9.92
• Structured Deep Hashing With Convolutional Neural Networks For Fast Person Re-identification (2017)12.87