offical implement of our Lifelong Person Re-Identification via Adaptive Knowledge Accumulation in CVPR2021

Overview

LifelongReID

Offical implementation of our Lifelong Person Re-Identification via Adaptive Knowledge Accumulation in CVPR2021 by Nan Pu, Wei Chen, Yu Liu, Erwin M. Bakker and Michael S. Lew.

We provide a lifelong person reid toolbox lreid in this repo.

More details please see our paper.

Framework

Citation

@InProceedings{pu_cvpr2021,
author = {Pu, Nan and Chen, Wei and Liu, Yu and Bakker, Erwin M. and Lew, Michael S.},
title = {Lifelong Person Re-Identification via Adaptive Knowledge Accumulation},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2021}
}

Install

Enviornment

conda create -n lreid python=3.7
conda activate lreid
conda install pytorch==1.4.0 torchvision==0.5.0 cudatoolkit=10.0 -c pytorch
conda install opencv
pip install Cython sklearn numpy prettytable easydict tqdm matplotlib

For visualization, you might need to install visdom:

pip install visdom

If you want to use fp16, please follow https://github.com/NVIDIA/apex to install apex, which is just a optional pakage. The following codes work in our enviroment, but it could not work on other enviroment.

git clone https://github.com/NVIDIA/apex
cd apex
pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./

lreid toolbox

Then, you could clone our project and install lreid

git clone https://github.com/TPCD/LifelongReID
cd LifelongReID
python setup.py develop

Dataset prepration

Please follow Torchreid_Dataset_Doc to download datasets and unzip them to your data path (we refer to 'machine_dataset_path' in train_test.py). Alternatively, you could download some of unseen-domain datasets in DualNorm.

Train & Test

python train_test.py

Acknowledgement

The code is based on the PyTorch implementation of the Torchreid and Person_reID_baseline_pytorch.

You might also like...
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,

 Person Re-identification
Person Re-identification

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

Experiment about Deep Person Re-identification with EfficientNet-v2
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.

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

Joint Discriminative and Generative Learning for Person Re-identification. CVPR'19 (Oral)
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

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

[BMVC2021] The official implementation of
[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

Exploiting Robust Unsupervised Video Person Re-identification
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

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

Comments
  • Unsatisfactory Results on CUHK, DUKE and MSMT17

    Unsatisfactory Results on CUHK, DUKE and MSMT17

    Hi Nan, Thanks for sharing code. I managed to reproduce the results on all SEEN domains, but found, except for Market1501, there are great differences camparing with the results reported in the paper. So, how can I reproduce the results on CUHK, DUKE and MSMT17? Do I need to modify the dataloader or something?

    opened by hh23333 0
  • Results on CUHK-SYSU and MSMT17

    Results on CUHK-SYSU and MSMT17

    Thanks for your code. I managed to reproduce the results for Market, Duke and CUHK03. However, I tried to add CUHK-SYSU and MSMT17 into argument --test_dataset, which could not give results mentioned in the paper. The test_mode argument seems to be not working in test_p_s.py, while test_continual_operation_neck.py only support market/duke/mix. Could you please share more details on how to test CUHK-SYSU and MSMT17 datasets?

    opened by chenhao2345 13
  • What about the change of results in Market during adding new domains?

    What about the change of results in Market during adding new domains?

    Thank you for your sharing! In the paper, you give the final performance of Market, but I am curious about the performance change of Market during training, i.e., will the performance on Market decrease after the training on SYSU?

    opened by pansanity666 3
Owner
PeterPu
Growth is like training a deep neural network, which needs supervision and finetunes.
PeterPu
PyTorch implementation of the Deep SLDA method from our CVPRW-2020 paper "Lifelong Machine Learning with Deep Streaming Linear Discriminant Analysis"

Lifelong Machine Learning with Deep Streaming Linear Discriminant Analysis This is a PyTorch implementation of the Deep Streaming Linear Discriminant

Tyler Hayes 41 Dec 25, 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
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
AirLoop: Lifelong Loop Closure Detection

AirLoop This repo contains the source code for paper: Dasong Gao, Chen Wang, Sebastian Scherer. "AirLoop: Lifelong Loop Closure Detection." arXiv prep

Chen Wang 53 Jan 3, 2023
PyTorch implementation of our Adam-NSCL algorithm from our CVPR2021 (oral) paper "Training Networks in Null Space for Continual Learning"

Adam-NSCL This is a PyTorch implementation of Adam-NSCL algorithm for continual learning from our CVPR2021 (oral) paper: Title: Training Networks in N

Shipeng Wang 34 Dec 21, 2022
Unofficial implement with paper SpeakerGAN: Speaker identification with conditional generative adversarial network

Introduction This repository is about paper SpeakerGAN , and is unofficially implemented by Mingming Huang ([email protected]), Tiezheng Wang (wtz920729

null 7 Jan 3, 2023
Pytorch implementation of CVPR2021 paper "MUST-GAN: Multi-level Statistics Transfer for Self-driven Person Image Generation"

MUST-GAN Code | paper The Pytorch implementation of our CVPR2021 paper "MUST-GAN: Multi-level Statistics Transfer for Self-driven Person Image Generat

TianxiangMa 46 Dec 26, 2022
Unsupervised Pre-training for Person Re-identification (LUPerson)

LUPerson Unsupervised Pre-training for Person Re-identification (LUPerson). The repository is for our CVPR2021 paper Unsupervised Pre-training for Per

null 143 Dec 24, 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