Hierarchical and Efficient Learning for Person Re-Identification

05/18/2020
by   Jiangning Zhang, et al.
7

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.

READ FULL TEXT

page 3

page 4

page 6

research
04/09/2018

Occluded Person Re-identification

Person re-identification (re-id) suffers from a serious occlusion proble...
research
10/16/2018

SCPNet: Spatial-Channel Parallelism Network for Joint Holistic and Partial Person Re-Identification

Holistic person re-identification (ReID) has received extensive study in...
research
07/23/2017

Person Re-identification Using Visual Attention

Despite recent attempts for solving the person re-identification problem...
research
07/24/2018

Partial Person Re-identification with Alignment and Hallucination

Partial person re-identification involves matching pedestrian frames whe...
research
11/30/2015

Hierarchical Invariant Feature Learning with Marginalization for Person Re-Identification

This paper addresses the problem of matching pedestrians across multiple...
research
03/29/2021

Learning Domain Invariant Representations for Generalizable Person Re-Identification

Generalizable person Re-Identification (ReID) has attracted growing atte...

Please sign up or login with your details

Forgot password? Click here to reset