Unsupervised Pre-training for Person Re-identification
- URL: http://arxiv.org/abs/2012.03753v2
- Date: Sun, 25 Apr 2021 04:51:41 GMT
- Title: Unsupervised Pre-training for Person Re-identification
- Authors: Dengpan Fu, Dongdong Chen, Jianmin Bao, Hao Yang, Lu Yuan, Lei Zhang,
Houqiang Li, Dong Chen
- Abstract summary: We present a large scale unlabeled person re-identification (Re-ID) dataset "LUPerson"
We make the first attempt of performing unsupervised pre-training for improving the generalization ability of the learned person Re-ID feature representation.
- Score: 90.98552221699508
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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.
Related papers
- Synthesizing Efficient Data with Diffusion Models for Person Re-Identification Pre-Training [51.87027943520492]
We present a novel paradigm Diffusion-ReID to efficiently augment and generate diverse images based on known identities.
Benefiting from our proposed paradigm, we first create a new large-scale person Re-ID dataset Diff-Person, which consists of over 777K images from 5,183 identities.
arXiv Detail & Related papers (2024-06-10T06:26:03Z) - Benchmarking person re-identification datasets and approaches for
practical real-world implementations [1.0079626733116613]
Person Re-Identification (Re-ID) has received a lot of attention.
However, when such Re-ID models are deployed in new cities or environments, the task of searching for people within a network of security cameras is likely to face an important domain shift.
This paper introduces a complete methodology to evaluate Re-ID approaches and training datasets with respect to their suitability for unsupervised deployment for live operations.
arXiv Detail & Related papers (2022-12-20T03:45:38Z) - Unleashing the Potential of Unsupervised Pre-Training with
Intra-Identity Regularization for Person Re-Identification [10.045028405219641]
We design an Unsupervised Pre-training framework for ReID based on the contrastive learning (CL) pipeline, dubbed UP-ReID.
We introduce an intra-identity (I$2$-)regularization in the UP-ReID, which is instantiated as two constraints coming from global image aspect and local patch aspect.
Our UP-ReID pre-trained model can significantly benefit the downstream ReID fine-tuning and achieve state-of-the-art performance.
arXiv Detail & Related papers (2021-12-01T07:16:37Z) - Self-Supervised Pre-Training for Transformer-Based Person
Re-Identification [54.55281692768765]
Transformer-based supervised pre-training achieves great performance in person re-identification (ReID)
Due to the domain gap between ImageNet and ReID datasets, it usually needs a larger pre-training dataset to boost the performance.
This work aims to mitigate the gap between the pre-training and ReID datasets from the perspective of data and model structure.
arXiv Detail & Related papers (2021-11-23T18:59:08Z) - Unsupervised Domain Adaptive Learning via Synthetic Data for Person
Re-identification [101.1886788396803]
Person re-identification (re-ID) has gained more and more attention due to its widespread applications in video surveillance.
Unfortunately, the mainstream deep learning methods still need a large quantity of labeled data to train models.
In this paper, we develop a data collector to automatically generate synthetic re-ID samples in a computer game, and construct a data labeler to simultaneously annotate them.
arXiv Detail & Related papers (2021-09-12T15:51:41Z) - Semi-Supervised Domain Generalizable Person Re-Identification [74.75528879336576]
Existing person re-identification (re-id) methods are stuck when deployed to a new unseen scenario.
Recent efforts have been devoted to domain adaptive person re-id where extensive unlabeled data in the new scenario are utilized in a transductive learning manner.
We aim to explore multiple labeled datasets to learn generalized domain-invariant representations for person re-id.
arXiv Detail & Related papers (2021-08-11T06:08:25Z) - Domain Adaptive Egocentric Person Re-identification [10.199631830749839]
Person re-identification (re-ID) in first-person (egocentric) vision is a fairly new and unexplored problem.
With the increase of wearable video recording devices, egocentric data becomes readily available.
There is a significant lack of large scale structured egocentric datasets for person re-identification.
arXiv Detail & Related papers (2021-03-08T16:19:32Z) - Fine-Grained Re-Identification [1.8275108630751844]
This paper proposes a computationally efficient fine-grained ReID model, FGReID, which is among the first models to unify image and video ReID.
FGReID takes advantage of video-based pre-training and spatial feature attention to improve performance on both video and image ReID tasks.
arXiv Detail & Related papers (2020-11-26T21:04:17Z) - Intra-Camera Supervised Person Re-Identification [87.88852321309433]
We propose a novel person re-identification paradigm based on an idea of independent per-camera identity annotation.
This eliminates the most time-consuming and tedious inter-camera identity labelling process.
We formulate a Multi-tAsk mulTi-labEl (MATE) deep learning method for Intra-Camera Supervised (ICS) person re-id.
arXiv Detail & Related papers (2020-02-12T15:26:33Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.