This is Official implementation for "Pose-guided Feature Disentangling for Occluded Person Re-Identification Based on Transformer" in AAAI2022

Last update: Dec 18, 2022

Related tags

Overview

PFD：Pose-guided Feature Disentangling for Occluded Person Re-identification based on Transformer

This repo is the official implementation of "Pose-guided Feature Disentangling for Occluded Person Re-identification based on Transformer(PFD), Tao Wang, Hong Liu, Pinghao Song, Tianyu Guo& Wei Shi" in PyTorch.

Pipeline

Dependencies

timm==0.3.2
torch==1.6.0
numpy==1.20.2
yacs==0.1.8
opencv_python==4.5.2.54
torchvision==0.7.0
Pillow==8.4.0

Installation

pip install -r requirements.txt

If you find some packages are missing, please install them manually.

Prepare Datasets

mkdir data

Please download the dataset, and then rename and unzip them under the data

data
|--market1501
|
|--Occluded_Duke
|
|--Occluded_REID
|
|--MSMT17
|
|--dukemtmcreid

Prepare ViT Pre-trained and HRNet Pre-trained Models

mkdir data

The ViT Pre-trained model can be found in ViT_Base, The HRNet Pre-trained model can be found in HRNet, please download it and put in the './weights' dictory.

Training

We use One GeForce GTX 1080Ti GPU for Training Before train the model, please modify the parameters in config file, please refer to Arguments in TransReID

python occ_train.py --config_file {config_file path}
#example
python occ_train.py --config_file 'configs/OCC_Duke/skeleton_pfd.yml'

Test the model

First download the Occluded-Duke model:Occluded-Duke

To test on pretrained model on Occ-Duke: Modify the pre-trained model path (PRETRAIN_PATH:ViT_Base, POSE_WEIGHT:HRNet, WEIGHT:Occluded-Duke) in yml, and then run:

## OccDuke for example
python test.py --config_file 'configs/OCC_Duke/skeleton_pfd.yml'

Occluded-Duke Results

Model	Image Size	Rank-1	mAP
HOReID	256*128	55.1	43.8
PAT	256*128	64.5	53.6
TransReID	256*128	64.2	55.7
PFD	256*128	67.7	60.1
TransReID*	256*128	66.4	59.2
PFD*	256*128	69.5	61.8

$*$means the encoder is with a small step sliding-window setting

Occluded-REID Results

Model	Image Size	Rank-1	mAP
HOReID	256*128	80.3	70.2
PAT	256*128	81.6	72.1
PFD	256*128	79.8	81.3

Market-1501 Results

Model	Image Size	Rank-1	mAP
HOReID	256*128	80.3	70.2
PAT	256*128	95.4	88.0
TransReID	256*128	95.4	88.0
PFD	256*128	95.5	89.6

Citation

If you find our work useful in your research, please consider citing this paper! (preprint version will be available soon)

@inproceedings{wang2022pfd,
  Title= {Pose-guided Feature Disentangling for Occluded Person Re-identification based on Transformer},
  Author= {Tao Wang, Hong Liu, Pinhao Song, Tianyu Guo and Wei Shi},
  Booktitle= {AAAI},
  Year= {2022}
}

Acknowledgement

Our code is extended from the following repositories. We thank the authors for releasing the codes.

License

This project is licensed under the terms of the MIT license.

Official pytorch implementation of paper "Inception Convolution with Efficient Dilation Search" (CVPR 2021 Oral).

IC-Conv This repository is an official implementation of the paper Inception Convolution with Efficient Dilation Search. Getting Started Download Imag

111 Dec 31, 2022

Official PyTorch Implementation of Unsupervised Learning of Scene Flow Estimation Fusing with Local Rigidity

UnRigidFlow This is the official PyTorch implementation of UnRigidFlow (IJCAI2019). Here are two sample results (~10MB gif for each) of our unsupervis

28 Nov 16, 2022

Official implementation of our paper "LLA: Loss-aware Label Assignment for Dense Pedestrian Detection" in Pytorch.

LLA: Loss-aware Label Assignment for Dense Pedestrian Detection This project provides an implementation for "LLA: Loss-aware Label Assignment for Dens

35 Dec 6, 2022

Official implementation of Self-supervised Graph Attention Networks (SuperGAT), ICLR 2021.

SuperGAT Official implementation of Self-supervised Graph Attention Networks (SuperGAT). This model is presented at How to Find Your Friendly Neighbor

127 Dec 28, 2022

An official implementation of "SFNet: Learning Object-aware Semantic Correspondence" (CVPR 2019, TPAMI 2020) in PyTorch.

PyTorch implementation of SFNet This is the implementation of the paper "SFNet: Learning Object-aware Semantic Correspondence". For more information,

87 Dec 30, 2022

This project is the official implementation of our accepted ICLR 2021 paper BiPointNet: Binary Neural Network for Point Clouds.

BiPointNet: Binary Neural Network for Point Clouds Created by Haotong Qin, Zhongang Cai, Mingyuan Zhang, Yifu Ding, Haiyu Zhao, Shuai Yi, Xianglong Li

59 Dec 17, 2022

Official code implementation for "Personalized Federated Learning using Hypernetworks"

Personalized Federated Learning using Hypernetworks This is an official implementation of Personalized Federated Learning using Hypernetworks paper. [

121 Dec 25, 2022

StyleGAN2 - Official TensorFlow Implementation

10.1k Dec 28, 2022

Old Photo Restoration (Official PyTorch Implementation)

Bringing Old Photo Back to Life (CVPR 2020 oral)

11.3k Dec 30, 2022

Comments

精度达不到论文里面的数据

作者您好，我在1501上测试了一下就改了 /home/zqx_3090/PersonReID/PersonReID2/PFD_Net-master/configs/Market1501/skeleton_pfd.yml 这个文件，里面的参数并没有改动改了权重的路径，和文件夹的路径其他都没变，如何训练300轮次后我选择最高300轮的 /home/zqx_3090/PersonReID/PersonReID2/PFD_Net-master/logs/Market/pfd_net/skeleton_transformer_300.pth 去测试结果是： 2021-12-28 18:23:39,417 PFDreid.test INFO: Validation Results 2021-12-28 18:23:39,417 PFDreid.test INFO: mAP: 88.2% 2021-12-28 18:23:39,418 PFDreid.test INFO: CMC curve, Rank-1 :94.8% 2021-12-28 18:23:39,418 PFDreid.test INFO: CMC curve, Rank-5 :98.3% 2021-12-28 18:23:39,418 PFDreid.test INFO: CMC curve, Rank-10 :99.0% 达不到论文的95.5 甚至不如TransReID的精度？？？您能看看是为什么嘛？

MODEL: PRETRAIN_CHOICE: 'imagenet' PRETRAIN_PATH: '/home/zqx_3090/PersonReID/PersonReID2/PFD_Net-master/weights/jx_vit_base_p16_224-80ecf9dd.pth' METRIC_LOSS_TYPE: 'triplet' IF_LABELSMOOTH: 'on' IF_WITH_CENTER: 'no' NAME: 'skeleton_transformer' NO_MARGIN: True DEVICE_ID: ('2') TRANSFORMER_TYPE: 'vit_base_patch16_224_TransReID' STRIDE_SIZE: [16, 16]

SIE_CAMERA: True SIE_COE: 3.0 JPM: True RE_ARRANGE: True NUM_HEAD: 8 DECODER_DROP_RATE: 0.1 DROP_FIRST: False NUM_DECODER_LAYER: 6 QUERY_NUM: 17 POSE_WEIGHT: '/home/zqx_3090/PersonReID/PersonReID2/PFD_Net-master/weights/pose_hrnet_w48_384x288.pth' SKT_THRES: 0.2

INPUT: SIZE_TRAIN: [256, 128] SIZE_TEST: [256, 128] PROB: 0.5 # random horizontal flip RE_PROB: 0.5 # random erasing PADDING: 10 PIXEL_MEAN: [0.5, 0.5, 0.5] PIXEL_STD: [0.5, 0.5, 0.5]

DATASETS: NAMES: ('market1501') ROOT_DIR: ('/home/zqx_3090/PersonReID/PersonReID2/PFD_Net-master/data/')

DATALOADER: SAMPLER: 'softmax_triplet' NUM_INSTANCE: 4 NUM_WORKERS: 8

SOLVER: OPTIMIZER_NAME: 'SGD' MAX_EPOCHS: 300 BASE_LR: 0.008 IMS_PER_BATCH: 64 WARMUP_METHOD: 'linear' LARGE_FC_LR: False CHECKPOINT_PERIOD: 60 LOG_PERIOD: 50 EVAL_PERIOD: 30 WEIGHT_DECAY: 1e-4 WEIGHT_DECAY_BIAS: 1e-4 BIAS_LR_FACTOR: 2

TEST: EVAL: True IMS_PER_BATCH: 256 RE_RANKING: False WEIGHT: "/home/zqx_3090/PersonReID/PersonReID2/PFD_Net-master/logs/Market/pfd_net/skeleton_transformer_300.pth" #put your own pth NECK_FEAT: 'before' FEAT_NORM: 'yes'

OUTPUT_DIR: 'logs/Market/pfd_net'

opened by zqx951102 3
使用您的Occluded-Duke的预训练模型达不到文中的结果

作者您好：感谢你做出如此优秀的工作，我按照reademe的要求在使用您的Occluded-Duke的预训练模型时，发现达不到文中所说的结果，下图是我测试的结果：跟论文中的结果大约相差2%，我使用的时pytorch1.7.1, cuda10.2, python3.7.13;所以我想知道这是什么原因造成的呢？期待您的回复。

opened by changshuowang 2
There is no Occlude-REID data loader

Good work! I respect your contributions!

I want to testing Occluded-REID dataset in your code, but there is no loader. In your code, dataset.make_dataloader.py, line 14 "from .occ_reid import Occluded_REID"

Would you share this code?

thank you

opened by intlabSeJun 4

Releases(V1.0.0)

Owner

Tao Wang

GitHub Repository

Ladder Variational Autoencoders (LVAE) in PyTorch

Ladder Variational Autoencoders (LVAE) PyTorch implementation of Ladder Variational Autoencoders (LVAE) [1]: where the variational distributions q at

63 Dec 22, 2022

Multi-label Co-regularization for Semi-supervised Facial Action Unit Recognition (NeurIPS 2019)

MLCR This is the source code for paper Multi-label Co-regularization for Semi-supervised Facial Action Unit Recognition. Xuesong Niu, Hu Han, Shiguang

60 Nov 29, 2022

Lua-parser-lark - An out-of-box Lua parser written in Lark

An out-of-box Lua parser written in Lark Such parser handles a relaxed version o

2 Jul 19, 2022

Unofficial TensorFlow implementation of Protein Interface Prediction using Graph Convolutional Networks.

[TensorFlow] Protein Interface Prediction using Graph Convolutional Networks Unofficial TensorFlow implementation of Protein Interface Prediction usin

9 Oct 25, 2022

SeMask: Semantically Masked Transformers for Semantic Segmentation.

SeMask: Semantically Masked Transformers Jitesh Jain, Anukriti Singh, Nikita Orlov, Zilong Huang, Jiachen Li, Steven Walton, Humphrey Shi This repo co

186 Dec 30, 2022

Fast mesh denoising with data driven normal filtering using deep variational autoencoders

Fast mesh denoising with data driven normal filtering using deep variational autoencoders This is an implementation for the paper entitled "Fast mesh

9 Dec 02, 2022

PyTorch implementations of the paper: "Learning Independent Instance Maps for Crowd Localization"

IIM - Crowd Localization This repo is the official implementation of paper: Learning Independent Instance Maps for Crowd Localization. The code is dev

91 Nov 10, 2022

The Self-Supervised Learner can be used to train a classifier with fewer labeled examples needed using self-supervised learning.

Published by SpaceML • About SpaceML • Quick Colab Example Self-Supervised Learner The Self-Supervised Learner can be used to train a classifier with

92 Nov 30, 2022