Exploring Spatial Significance via Hybrid Pyramidal Graph Network for Vehicle Re-identification

29 May 2020  ·  Fei Shen, Jianqing Zhu, Xiaobin Zhu, Yi Xie, Jingchang Huang ·

Existing vehicle re-identification methods commonly use spatial pooling operations to aggregate feature maps extracted via off-the-shelf backbone networks. They ignore exploring the spatial significance of feature maps, eventually degrading the vehicle re-identification performance. In this paper, firstly, an innovative spatial graph network (SGN) is proposed to elaborately explore the spatial significance of feature maps. The SGN stacks multiple spatial graphs (SGs). Each SG assigns feature map's elements as nodes and utilizes spatial neighborhood relationships to determine edges among nodes. During the SGN's propagation, each node and its spatial neighbors on an SG are aggregated to the next SG. On the next SG, each aggregated node is re-weighted with a learnable parameter to find the significance at the corresponding location. Secondly, a novel pyramidal graph network (PGN) is designed to comprehensively explore the spatial significance of feature maps at multiple scales. The PGN organizes multiple SGNs in a pyramidal manner and makes each SGN handles feature maps of a specific scale. Finally, a hybrid pyramidal graph network (HPGN) is developed by embedding the PGN behind a ResNet-50 based backbone network. Extensive experiments on three large scale vehicle databases (i.e., VeRi776, VehicleID, and VeRi-Wild) demonstrate that the proposed HPGN is superior to state-of-the-art vehicle re-identification approaches.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Vehicle Re-Identification VehicleID Small HPGN mAP 89.6 # 3
Rank1 83.91 # 3
Vehicle Re-Identification VeRi-776 HPGN mAP 80.18 # 11
Rank1 96.72 # 5

Methods


No methods listed for this paper. Add relevant methods here