Rethinking of Pedestrian Attribute Recognition: A Reliable Evaluation under Zero-Shot Pedestrian Identity Setting

Overview

Rethinking of Pedestrian Attribute Recognition: A Reliable Evaluation under Zero-Shot Pedestrian Identity Setting (official Pytorch implementation)

zero-shot This paper submitted to TIP is the extension of the previous Arxiv paper.

This project aims to

  1. provide a baseline of pedestrian attribute recognition.
  2. provide two new datasets RAPzs and PETAzs following zero-shot pedestrian identity setting.
  3. provide a general training pipeline for pedestrian attribute recognition and multi-label classification task.

This project provide

  1. DDP training, which is mainly used for multi-label classifition.
  2. Training on all attributes, testing on "selected" attribute. Because the proportion of positive samples for other attributes is less than a threshold, such as 0.01.
    1. For PETA and PETAzs, 35 of the 105 attributes are selected for performance evaluation.
    2. For RAPv1, 51 of the 92 attributes are selected for performance evaluation.
    3. For RAPv2 and RAPzs, 54 and 53 of the 152 attributes are selected for performance evaluation.
    4. For PA100k, all attributes are selected for performance evaluation.
    • However, training on all attributes can not bring consistent performance improvement on various datasets.
  3. EMA model.
  4. Transformer-base model, such as swin-transformer (with a huge performance improvement) and vit.
  5. Convenient dataset info file like dataset_all.pkl

Dataset Info

  • PETA: Pedestrian Attribute Recognition At Far Distance [Paper][Project]

  • PA100K[Paper][Github]

  • RAP : A Richly Annotated Dataset for Pedestrian Attribute Recognition

  • PETAzs & RAPzs : Rethinking of Pedestrian Attribute Recognition: A Reliable Evaluation under Zero-Shot Pedestrian Identity Setting Paper [Project]

Performance

Pedestrian Attribute Recognition

Datasets Models ma Acc Prec Rec F1
PA100k resnet50 80.21 79.15 87.79 87.01 87.40
-- resnet50* 79.85 79.13 89.45 85.40 87.38
-- resnet50 + EMA 81.97 80.20 88.06 88.17 88.11
-- bninception 79.13 78.19 87.42 86.21 86.81
-- TresnetM 74.46 68.72 79.82 80.71 80.26
-- swin_s 82.19 80.35 87.85 88.51 88.18
-- vit_s 79.40 77.61 86.41 86.22 86.32
-- vit_b 81.01 79.38 87.60 87.49 87.55
PETA resnet50 83.96 78.65 87.08 85.62 86.35
PETAzs resnet50 71.43 58.69 74.41 69.82 72.04
RAPv1 resnet50 79.27 67.98 80.19 79.71 79.95
RAPv2 resnet50 78.52 66.09 77.20 80.23 78.68
RAPzs resnet50 71.76 64.83 78.75 76.60 77.66
  • The resnet* model is trained by using the weighted function proposed by Tan in AAAI2020.
  • Performance in PETAzs and RAPzs based on the first version of PETAzs and RAPzs as described in paper.
  • Experiments are conducted on the input size of (256, 192), so there may be minor differences from the results in the paper.
  • The reported performance can be achieved at the first drop of learning rate. We also take this model as the best model.
  • Pretrained models are provided now at Google Drive.

Multi-label Classification

Datasets Models mAP CP CR CF1 OP OR OF1
COCO resnet101 82.75 84.17 72.07 77.65 85.16 75.47 80.02

Pretrained Models

Dependencies

  • python 3.7
  • pytorch 1.7.0
  • torchvision 0.8.2
  • cuda 10.1

Get Started

  1. Run git clone https://github.com/valencebond/Rethinking_of_PAR.git
  2. Create a directory to dowload above datasets.
    cd Rethinking_of_PAR
    mkdir data
    
  3. Prepare datasets to have following structure:
    ${project_dir}/data
        PETA
            images/
            PETA.mat
            dataset_all.pkl
            dataset_zs_run0.pkl
        PA100k
            data/
            dataset_all.pkl
        RAP
            RAP_dataset/
            RAP_annotation/
            dataset_all.pkl
        RAP2
            RAP_dataset/
            RAP_annotation/
            dataset_zs_run0.pkl
        COCO14
            train2014/
            val2014/
            ml_anno/
                category.json
                coco14_train_anno.pkl
                coco14_val_anno.pkl
    
  4. Train baseline based on resnet50
    sh train.sh
    

Acknowledgements

Codes are based on the repository from Dangwei Li and Houjing Huang. Thanks for their released code.

Citation

If you use this method or this code in your research, please cite as:

@article{jia2021rethinking,
  title={Rethinking of Pedestrian Attribute Recognition: A Reliable Evaluation under Zero-Shot Pedestrian Identity Setting},
  author={Jia, Jian and Huang, Houjing and Chen, Xiaotang and Huang, Kaiqi},
  journal={arXiv preprint arXiv:2107.03576},
  year={2021}
}
Owner
Jian
computer vision
Jian
MPI-IS Mesh Processing Library

Perceiving Systems Mesh Package This package contains core functions for manipulating meshes and visualizing them. It requires Python 3.5+ and is supp

Max Planck Institute for Intelligent Systems 494 Jan 06, 2023
Randstad Artificial Intelligence Challenge (powered by VGEN). Soluzione proposta da Stefano Fiorucci (anakin87) - primo classificato

Randstad Artificial Intelligence Challenge (powered by VGEN) Soluzione proposta da Stefano Fiorucci (anakin87) - primo classificato Struttura director

Stefano Fiorucci 1 Nov 13, 2021
[TIP 2020] Multi-Temporal Scene Classification and Scene Change Detection with Correlation based Fusion

Multi-Temporal Scene Classification and Scene Change Detection with Correlation based Fusion Code for Multi-Temporal Scene Classification and Scene Ch

Lixiang Ru 33 Dec 12, 2022
Implementation for Stankevičiūtė et al. "Conformal time-series forecasting", NeurIPS 2021.

Conformal time-series forecasting Implementation for Stankevičiūtė et al. "Conformal time-series forecasting", NeurIPS 2021. If you use our code in yo

Kamilė Stankevičiūtė 36 Nov 21, 2022
LRBoost is a scikit-learn compatible approach to performing linear residual based stacking/boosting.

LRBoost is a sckit-learn compatible package for linear residual boosting. LRBoost combines a linear estimator and a non-linear estimator to leverage t

Andrew Patton 5 Nov 23, 2022
Official code for the publication "HyFactor: Hydrogen-count labelled graph-based defactorization Autoencoder".

HyFactor Graph-based architectures are becoming increasingly popular as a tool for structure generation. Here, we introduce a novel open-source archit

Laboratoire-de-Chemoinformatique 11 Oct 10, 2022
Learning to Disambiguate Strongly Interacting Hands via Probabilistic Per-Pixel Part Segmentation [3DV 2021 Oral]

Learning to Disambiguate Strongly Interacting Hands via Probabilistic Per-Pixel Part Segmentation [3DV 2021 Oral] Learning to Disambiguate Strongly In

Zicong Fan 40 Dec 22, 2022
DEEPAGÉ: Answering Questions in Portuguese about the Brazilian Environment

DEEPAGÉ: Answering Questions in Portuguese about the Brazilian Environment This repository is related to the paper DEEPAGÉ: Answering Questions in Por

0 Dec 10, 2021
TransCD: Scene Change Detection via Transformer-based Architecture

TransCD: Scene Change Detection via Transformer-based Architecture

wangzhixue 29 Dec 11, 2022
Example of semantic segmentation in Keras

keras-semantic-segmentation-example Example of semantic segmentation in Keras Single class example: Generated data: random ellipse with random color o

53 Mar 23, 2022
This repository contains tutorials for the py4DSTEM Python package

py4DSTEM Tutorials This repository contains tutorials for the py4DSTEM Python package. For more information about py4DSTEM, including installation ins

11 Dec 23, 2022
Deepface is a lightweight face recognition and facial attribute analysis (age, gender, emotion and race) framework for python

deepface Deepface is a lightweight face recognition and facial attribute analysis (age, gender, emotion and race) framework for python. It is a hybrid

Kushal Shingote 2 Feb 10, 2022
pytorchのスライス代入操作をonnxに変換する際にScatterNDならないようにするサンプル

pytorch_remove_ScatterND pytorchのスライス代入操作をonnxに変換する際にScatterNDならないようにするサンプル。 スライスしたtensorにそのまま代入してしまうとScatterNDになるため、計算結果をcatで新しいtensorにする。 python ver

2 Dec 01, 2022
Continual World is a benchmark for continual reinforcement learning

Continual World Continual World is a benchmark for continual reinforcement learning. It contains realistic robotic tasks which come from MetaWorld. Th

41 Dec 24, 2022
Malware Bypass Research using Reinforcement Learning

Malware Bypass Research using Reinforcement Learning

Bobby Filar 76 Dec 26, 2022
PyTorch implementation of Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D Pose

Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D Pose Release Notes The official PyTorch implementation of Neural View S

Angtian Wang 20 Oct 09, 2022
This is a GUI interface which can process forest fire detection, smoke detection and fire segmentation

This is a GUI interface which can process forest fire detection, smoke detection and fire segmentation. Yolov5 is used to detect fire and smoke and unet is used to segment fire.

7 Jan 08, 2023
Rafael Project- Classifying rockets to different types using data science algorithms.

Rocket-Classify Rafael Project- Classifying rockets to different types using data science algorithms. In this project we received data base with data

Hadassah Engel 5 Sep 18, 2021
QuanTaichi evaluation suite

QuanTaichi: A Compiler for Quantized Simulations (SIGGRAPH 2021) Yuanming Hu, Jiafeng Liu, Xuanda Yang, Mingkuan Xu, Ye Kuang, Weiwei Xu, Qiang Dai, W

Taichi Developers 120 Jan 04, 2023
Generalized and Efficient Blackbox Optimization System.

OpenBox Doc | OpenBox中文文档 OpenBox: Generalized and Efficient Blackbox Optimization System OpenBox is an efficient and generalized blackbox optimizatio

DAIR Lab 238 Dec 29, 2022