Person re-identification across different datasets with multi-task learning

TL;DR

This paper introduces a multi-task CNN approach for person re-identification that leverages diverse datasets with different annotations to improve performance across multiple conditions.

Contribution

The paper proposes a multi-task learning framework that combines various dataset annotations and loss functions to enhance cross-dataset person re-identification performance.

Findings

The method outperforms recent re-identification approaches on two datasets.

Multi-task learning improves generalization across datasets with different conditions.

Using multiple losses helps extract richer features for re-identification.

Abstract

This paper presents an approach to tackle the re-identification problem. This is a challenging problem due to the large variation of pose, illumination or camera view. More and more datasets are available to train machine learning models for person re-identification. These datasets vary in conditions: cameras numbers, camera positions, location, season, in size, i.e. number of images, number of different identities. Finally in labeling: there are datasets annotated with attributes while others are not. To deal with this variety of datasets we present in this paper an approach to take information from different datasets to build a system which performs well on all of them. Our model is based on a Convolutional Neural Network (CNN) and trained using multitask learning. Several losses are used to extract the different information available in the different datasets. Our main task is learned with a classification loss. To reduce the intra-class variation we experiment with the center loss. Our paper ends with a performance evaluation in which we discuss the influence of the different losses on the global re-identification performance. We show that with our method, we are able to build a system that performs well on different datasets and simultaneously extracts attributes. We also show that our system outperforms recent re-identification works on two datasets.