Grafted network for person re-identification

2019/10/25 by Jiabao Wang, Yang Li, Shanshan Jiao +2 · 7 citations
Computer Science · Engineering · Mathematics · #Advanced Neural Network Applications #Algorithm #Artificial intelligence #Computation #Computer science #Convolutional neural network #Discriminative model #Feature (linguistics) #Gait Recognition and Analysis #Identification (biology) #Mathematics #Pattern recognition (psychology) #Rank (graph theory) #Representation (politics) #Rootstock #Video Surveillance and Tracking Methods #cs.CV

paper · pdf · doi:10.1016/j.image.2019.115674

published in Signal Processing Image Communication 80, 115674 (Elsevier BV)

openalex publication_date 2019/10/25 · arxiv created 2020/06/06 · arxiv updated 2020/06/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Abstract

Convolutional neural networks have shown outstanding effectiveness in person re-identification (re-ID). However, the models always have large number of parameters and much computation for mobile application. In order to relieve this problem, we propose a novel grafted network (GraftedNet), which is designed by grafting a high-accuracy rootstock and a light-weighted scion. The rootstock is based on the former parts of ResNet-50 to provide a strong baseline, while the scion is a new designed module, composed of the latter parts of SqueezeNet, to compress the parameters. To extract more discriminative feature representation, a joint multi-level and part-based feature is proposed. In addition, to train GraftedNet efficiently, we propose an accompanying learning method, by adding an accompanying branch to train the model in training and removing it in testing for saving parameters and computation. On three public person re-ID benchmarks (Market1501, DukeMTMC-reID and CUHK03), the effectiveness of GraftedNet are evaluated and its components are analyzed. Experimental results show that the proposed GraftedNet achieves 93.02%, 85.3% and 76.2% in Rank-1 and 81.6%, 74.7% and 71.6% in mAP, with only 4.6M parameters.

Citations

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Distilling the Knowledge in a Neural Network
• ImageNet classification with deep convolutional neural networks
• Person Re-identification: Past, Present and Future
• In Defense of the Triplet Loss for Person Re-Identification
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Random Erasing Data Augmentation
• Person re-identification with fusion of hand-crafted and deep pose-based body region features
• A Novel Teacher-Student Learning Framework For Occluded Person Re-Identification
• Pose-Invariant Embedding for Deep Person Re-Identification
• A Discriminatively Learned CNN Embedding for Person Reidentification
• Resource Aware Person Re-identification across Multiple Resolutions