Code Monkey home page Code Monkey logo

isp-reid's Introduction

ISP-reID

Codes for 'Identity-Guided Human Semantic Parsing for Person Re-Identification', accepted by ECCV2020 spotlight. We propose the Identity-Guided Human Semantic Parsing approach (ISP) to locate both the human body parts and personal belongings at pixel-level for person re-ID only with person identity labels. ISP-reID is based on the open project, reid strong baseline.

image

Installation

  1. 'cd' to folder where you want to download this repo

  2. Run 'git clone https://github.com/CASIA-IVA-Lab/ISP-reID.git'

  3. Install dependencies:

  4. Install faiss from faiss

Re-ID Dataset Preparation

Create a directory to store reid datasets under this repo or outside this repo. Remember to set your path to the root of the dataset in config/defaults.py for all training and testing or set in every single config file in configs/ or set in every single command.

Take 'DukeMTMC-reID' for exmaple:

Extract dataset to 'DukeMTMC-reID'. The data structure would like:

data
    DukeMTMC-reID
            bounding_box_test/
            bounding_box_train/
            bounding_box_train_parsing_pgt/
            ......

'bounding_box_train_parsing_pgt' is the predicted ground-truth generated by SCHP, which is only used for evaluating the performance of the parsing results of ISP. We have generated the predicted ground-truth for person re-ID datasets on PGT, code: m6n5.

Pre-trained Model Preparation

Download the pre-trained HRNet32 on ImageNet from Model, code: r1o2.

Train

For your convenience, we provide the bash scripts with our recommended settings. Please 'cd' to the root path of this repo and run:

bash ./ISP-*.sh

Reference

We hope that this technique will benefit more computer vision related applications and inspire more works. If you find this technique and repository useful, please cite the paper. Thanks!

@article{zhu2020identity,
  title={Identity-Guided Human Semantic Parsing for Person Re-Identification},
  author={Zhu, Kuan and Guo, Haiyun and Liu, Zhiwei and Tang, Ming and Wang, Jinqiao},
  journal={ECCV},
  year={2020}
}

isp-reid's People

Contributors

ivaopenlab avatar liyirui-git avatar zhukuan96 avatar

Stargazers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.