Unsupervised Pre-training for Person Re-identification (LUPerson)

Overview

LUPerson

Unsupervised Pre-training for Person Re-identification (LUPerson).

PWC PWC PWC PWC

The repository is for our CVPR2021 paper Unsupervised Pre-training for Person Re-identification.

LUPerson Dataset

LUPerson is currently the largest unlabeled dataset for Person Re-identification, which is used for Unsupervised Pre-training. LUPerson consists of 4M images of over 200K identities and covers a much diverse range of capturing environments.

Details can be found at ./LUP.

Pre-trained Models

Model path
ResNet50 R50
ResNet101 R101
ResNet152 R152

Finetuned Results

For MGN with ResNet50:

Dataset mAP cmc1 path
MSMT17 66.06/79.93 85.08/87.63 MSMT
DukeMTMC 82.27/91.70 90.35/92.82 Duke
Market1501 91.12/96.16 96.26/97.12 Market
CUHK03-L 74.54/85.84 74.64/82.86 CUHK03

These numbers are a little different from those reported in our paper, and most are slightly better.

For MGN with ResNet101:

Dataset mAP cmc1 path
MSMT17 68.41/81.12 86.28/88.27 -
DukeMTMC 84.15/92.77 91.88/93.99 -
Market1501 91.86/96.21 96.56/97.03 -
CUHK03-L 75.98/86.73 75.86/84.07 -

The numbers are in the format of without RR/with RR.

Citation

If you find this code useful for your research, please cite our paper.

@article{fu2020unsupervised,
  title={Unsupervised Pre-training for Person Re-identification},
  author={Fu, Dengpan and Chen, Dongdong and Bao, Jianmin and Yang, Hao and Yuan, Lu and Zhang, Lei and Li, Houqiang and Chen, Dong},
  journal={Proceedings of the IEEE conference on computer vision and pattern recognition},
  year={2021}
}
Comments
  • IBN ResNet pretraining

    IBN ResNet pretraining

    Hi Dengpan, Thanks for the great work! I am wondering if you are considering releasing pre-trained models with IBN-ResNet as backbones. It seems IBN is quite helpful for generalizable ReID, and perhaps even higher performance could be achieved with its help. (Or maybe you already did so -- that would be great too! In this case, do you mind sharing the models? That will be very valuable to me, thanks a lot!)

    opened by Zhongdao 2
  • How can i get LUP/lmdbs/lmdb

    How can i get LUP/lmdbs/lmdb

    In run_moco.sh ,There is --data_path "${DIR}/LUP/lmdbs/lmdb" however I can't found LUP/lmdbs/lmdb in my git clone. How can i get LUP/lmdbs/lmdb?

    opened by vanmeruso 1
  • Regarding the dataset extraction

    Regarding the dataset extraction

    Hi @DengpanFu Thanks for your work. Can you please help me in figuring out the extraction of data from youtube videos as the dets.pkl don't contain the resolution images and every youtube video is different in res when extracted

    opened by shreejalt 1
  • How to inference

    How to inference

    Hi,

    what a impressive concept from your paper

    I found demo.py in fast-reid/demo/ for inference, but I can't ensure arguments when running : python demo.py --config-file [arg1] --parallel -- opts MODEL.WEIGHTS [arg2]

    could you give a example ?

    opened by swingbalance 1
  • Questions about YouTube video resoluton

    Questions about YouTube video resoluton

    Thanks for excellent jobs and sharing from the authors! But I want to know if anyone solved the problem of the resolution of a certain video that should be downloaded?

    opened by YanzuoLu 0
  • About dataset downloading

    About dataset downloading

    Hi, thanks for your great work.

    How can I download LUPerson dataset?

    I can find LUPerson-NL dataset link but not the original LUPerson.

    Could you provide the way?

    opened by YangJae96 0
  • 如何解析dets中的pkl

    如何解析dets中的pkl

    感谢您的工作,您dets中的pkl解析后每个item是如下所示格式,请问各个字段依此代表什么(比如1819代表?),另外这个检测信息如何知道对应到视频中的哪个帧?多谢. 1819: [[0, {'bbox': array([ 618.625, 81.75 , 1031.375, 709.25 ], dtype=float32), 'pose': array([[733.08105, 205.53418], [753.5075 , 176.93718], [720.8252 , 185.10774], [822.95734, 176.93718], [724.91046, 193.27832], [929.1748 , 328.09277], [716.7399 , 340.34863], [986.36884, 524.1865 ], [692.2282 , 462.90723], [790.2751 , 597.7217 ], [667.7165 , 528.2718 ], [855.63965, 695.76855], [716.7399 , 691.6833 ], [773.9339 , 720.2803 ], [761.67804, 691.6833 ], [896.4925 , 699.8538 ], [684.0576 , 703.93915]], dtype=float32), 'conf': 0.9488497, 'prob': array([[0.960111 ], [0.9625488 ], [0.96105295], [0.9494078 ], [0.5803897 ], [0.7805291 ], [0.8539633 ], [0.84015006], [0.9082806 ], [0.85463387], [0.9051482 ], [0.68101335], [0.77411926], [0.01756088], [0.01273601], [0.07441353], [0.05114838]], dtype=float32)}]]

    opened by wang21jun 15
  • Errors in converting the torch models to ONNX

    Errors in converting the torch models to ONNX

    Following the steps mentioned in LUPerson/fast-reid/tools/deploy/ to export an ONNX file, and after running the below command (which I'm not 100% sure I got right):

    !python onnx_export.py --config-file ../../configs/CMDM/mgn_R50_moco.yml --name "baseline_R50" --output outputs/onnx_model --opts MODEL.WEIGHTS market_mgn_r50.pth

    I am getting the following error: AttributeError: module 'onnx' has no attribute 'optimizer'

    Any help would be appreciated, and possibly a clarification as to which exact yml and pth files should be used in order to export the MGN model trained from LUPerson pre-trained networks.

    opened by JosephAssaker 0
Owner
null
Self-Supervised Pre-Training for Transformer-Based Person Re-Identification

Self-Supervised Pre-Training for Transformer-Based Person Re-Identification [pdf] The official repository for Self-Supervised Pre-Training for Transfo

Hao Luo 45 Dec 3, 2021
Exploiting Robust Unsupervised Video Person Re-identification

Exploiting Robust Unsupervised Video Person Re-identification Implementation of the proposed uPMnet. For the preprint, please refer to [Arxiv]. Gettin

null 1 Apr 9, 2022
offical implement of our Lifelong Person Re-Identification via Adaptive Knowledge Accumulation in CVPR2021

LifelongReID Offical implementation of our Lifelong Person Re-Identification via Adaptive Knowledge Accumulation in CVPR2021 by Nan Pu, Wei Chen, Yu L

PeterPu 76 Dec 8, 2022
[TIP2020] Adaptive Graph Representation Learning for Video Person Re-identification

Introduction This is the PyTorch implementation for Adaptive Graph Representation Learning for Video Person Re-identification. Get started git clone h

WuYiming 41 Dec 12, 2022
[CVPR-2021] UnrealPerson: An adaptive pipeline for costless person re-identification

UnrealPerson: An Adaptive Pipeline for Costless Person Re-identification In our paper (arxiv), we propose a novel pipeline, UnrealPerson, that decreas

ZhangTianyu 70 Oct 10, 2022
IAUnet: Global Context-Aware Feature Learning for Person Re-Identification

IAUnet This repository contains the code for the paper: IAUnet: Global Context-Aware Feature Learning for Person Re-Identification Ruibing Hou, Bingpe

null 30 Jul 14, 2022
Implementation of "Learning Multi-Granular Hypergraphs for Video-Based Person Re-Identification"

hypergraph_reid Implementation of "Learning Multi-Granular Hypergraphs for Video-Based Person Re-Identification" If you find this help your research,

null 62 Dec 21, 2022
Person Re-identification

Person Re-identification Final project of Computer Vision Table of content Person Re-identification Table of content Students: Proposed method Dataset

Nguyễn Hoàng Quân 4 Jun 17, 2021
Experiment about Deep Person Re-identification with EfficientNet-v2

We evaluated the baseline with Resnet50 and Efficienet-v2 without using pretrained models. Also Resnet50-IBN-A and Efficientnet-v2 using pretrained on ImageNet. We used two datasets: Market-1501 and CUHK03.

lan.nguyen2k 77 Jan 3, 2023
Torchreid: Deep learning person re-identification in PyTorch.

Torchreid Torchreid is a library for deep-learning person re-identification, written in PyTorch. It features: multi-GPU training support both image- a

Kaiyang 3.7k Jan 5, 2023
Joint Discriminative and Generative Learning for Person Re-identification. CVPR'19 (Oral)

Joint Discriminative and Generative Learning for Person Re-identification [Project] [Paper] [YouTube] [Bilibili] [Poster] [Supp] Joint Discriminative

NVIDIA Research Projects 1.2k Dec 30, 2022
CM-NAS: Cross-Modality Neural Architecture Search for Visible-Infrared Person Re-Identification (ICCV2021)

CM-NAS Official Pytorch code of paper CM-NAS: Cross-Modality Neural Architecture Search for Visible-Infrared Person Re-Identification in ICCV2021. Vis

JDAI-CV 40 Nov 25, 2022
[BMVC2021] The official implementation of "DomainMix: Learning Generalizable Person Re-Identification Without Human Annotations"

DomainMix [BMVC2021] The official implementation of "DomainMix: Learning Generalizable Person Re-Identification Without Human Annotations" [paper] [de

Wenhao Wang 17 Dec 20, 2022
Paper: Cross-View Kernel Similarity Metric Learning Using Pairwise Constraints for Person Re-identification

Cross-View Kernel Similarity Metric Learning Using Pairwise Constraints for Person Re-identification T M Feroz Ali, Subhasis Chaudhuri, ICVGIP-20-21

T M Feroz Ali 3 Jun 17, 2022
Online Pseudo Label Generation by Hierarchical Cluster Dynamics for Adaptive Person Re-identification

Online Pseudo Label Generation by Hierarchical Cluster Dynamics for Adaptive Person Re-identification

TANG, shixiang 6 Nov 25, 2022
Open source person re-identification library in python

Open-ReID Open-ReID is a lightweight library of person re-identification for research purpose. It aims to provide a uniform interface for different da

Tong Xiao 1.3k Jan 1, 2023
Joint Detection and Identification Feature Learning for Person Search

Person Search Project This repository hosts the code for our paper Joint Detection and Identification Feature Learning for Person Search. The code is

null 712 Dec 17, 2022
Code of paper Interact, Embed, and EnlargE (IEEE): Boosting Modality-specific Representations for Multi-Modal Person Re-identification.

Interact, Embed, and EnlargE (IEEE): Boosting Modality-specific Representations for Multi-Modal Person Re-identification We provide the codes for repr

null 12 Dec 12, 2022
[CVPR2021 Oral] UP-DETR: Unsupervised Pre-training for Object Detection with Transformers

UP-DETR: Unsupervised Pre-training for Object Detection with Transformers This is the official PyTorch implementation and models for UP-DETR paper: @a

dddzg 430 Dec 23, 2022