FPB: Feature Pyramid Branch for Person Re-Identification

08/04/2021
by   Suofei Zhang, et al.
8

High performance person Re-Identification (Re-ID) requires the model to focus on both global silhouette and local details of pedestrian. To extract such more representative features, an effective way is to exploit deep models with multiple branches. However, most multi-branch based methods implemented by duplication of part backbone structure normally lead to severe increase of computational cost. In this paper, we propose a lightweight Feature Pyramid Branch (FPB) to extract features from different layers of networks and aggregate them in a bidirectional pyramid structure. Cooperated by attention modules and our proposed cross orthogonality regularization, FPB significantly prompts the performance of backbone network by only introducing less than 1.5M extra parameters. Extensive experimental results on standard benchmark datasets demonstrate that our proposed FPB based model outperforms state-of-the-art methods with obvious margin as well as much less model complexity. FPB borrows the idea of the Feature Pyramid Network (FPN) from prevailing object detection methods. To our best knowledge, it is the first successful application of similar structure in person Re-ID tasks, which empirically proves that pyramid network as affiliated branch could be a potential structure in related feature embedding models. The source code is publicly available at https://github.com/anocodetest1/FPB.git.

READ FULL TEXT

page 4

page 5

page 10

page 11

research
06/12/2020

Branch-Cooperative OSNet for Person Re-Identification

Multi-branch is extensively studied for learning rich feature representa...
research
08/11/2021

Person Re-identification via Attention Pyramid

In this paper, we propose an attention pyramid method for person re-iden...
research
01/16/2022

Global Regular Network for Writer Identification

Writer identification has practical applications for forgery detection a...
research
04/11/2017

Quality Aware Network for Set to Set Recognition

This paper targets on the problem of set to set recognition, which learn...
research
04/28/2022

A Closer Look at Branch Classifiers of Multi-exit Architectures

Multi-exit architectures consist of a backbone and branch classifiers th...
research
06/19/2019

A Strong Baseline and Batch Normalization Neck for Deep Person Re-identification

This study explores a simple but strong baseline for person re-identific...
research
01/15/2023

ACTIVE: A Deep Model for Sperm and Impurity Detection in Microscopic Videos

The accurate detection of sperms and impurities is a very challenging ta...

Please sign up or login with your details

Forgot password? Click here to reset