Unsupervised Pre-training for Person Re-identification

12/07/2020
by   Dengpan Fu, et al.
5

In this paper, we present a large scale unlabeled person re-identification (Re-ID) dataset "LUPerson" and make the first attempt of performing unsupervised pre-training for improving the generalization ability of the learned person Re-ID feature representation. This is to address the problem that all existing person Re-ID datasets are all of limited scale due to the costly effort required for data annotation. Previous research tries to leverage models pre-trained on ImageNet to mitigate the shortage of person Re-ID data but suffers from the large domain gap between ImageNet and person Re-ID data. LUPerson is an unlabeled dataset of 4M images of over 200K identities, which is 30X larger than the largest existing Re-ID dataset. It also covers a much diverse range of capturing environments (eg, camera settings, scenes, etc.). Based on this dataset, we systematically study the key factors for learning Re-ID features from two perspectives: data augmentation and contrastive loss. Unsupervised pre-training performed on this large-scale dataset effectively leads to a generic Re-ID feature that can benefit all existing person Re-ID methods. Using our pre-trained model in some basic frameworks, our methods achieve state-of-the-art results without bells and whistles on four widely used Re-ID datasets: CUHK03, Market1501, DukeMTMC, and MSMT17. Our results also show that the performance improvement is more significant on small-scale target datasets or under few-shot setting.

READ FULL TEXT
research
03/30/2022

Large-Scale Pre-training for Person Re-identification with Noisy Labels

This paper aims to address the problem of pre-training for person re-ide...
research
11/05/2018

Leveraging Virtual and Real Person for Unsupervised Person Re-identification

Person re-identification (re-ID) is a challenging problem especially whe...
research
04/16/2021

Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos

We introduce an approach for pre-training egocentric video models using ...
research
06/13/2019

Amur Tiger Re-identification in the Wild

Monitoring the population and movements of endangered species is an impo...
research
11/02/2022

Deep Multimodal Fusion for Generalizable Person Re-identification

Person re-identification plays a significant role in realistic scenarios...
research
12/02/2021

Stronger Baseline for Person Re-Identification

Person re-identification (re-ID) aims to identify the same person of int...
research
05/17/2021

Large-Scale Unsupervised Person Re-Identification with Contrastive Learning

Existing public person Re-Identification (ReID) datasets are small in mo...

Please sign up or login with your details

Forgot password? Click here to reset