Coder Social home page Coder Social logo

chnxindong / amr-loss Goto Github PK

View Code? Open in Web Editor NEW

This project forked from jacobzhaoziyuan/amr-loss

0.0 1.0 0.0 165 KB

[ICME 2022] Official Implementation for "Adaptive Mean-Residue Loss for Robust Facial Age Estimation"

License: MIT License

Shell 2.12% Python 97.88%

amr-loss's Introduction

Adaptive Mean-residue Loss for Robust Facial Age Estimation

ICME2022 ICME2022

Pytorch implementation of our method for ICME2022 paper: "Adaptive Mean-residue Loss for Robust Facial Age Estimation".

Abstract

Automated facial age estimation has diverse real-world applications in multimedia analysis, e.g., video surveillance, and human-computer interaction. However, due to the randomness and ambiguity of the aging process, age assessment is challenging. Most research work over the topic regards the task as one of age regression, classification, and ranking problems, and cannot well leverage age distribution in representing labels with age ambiguity. In this work, we propose a simple yet effective loss function for robust facial age estimation via distribution learning, i.e., adaptive mean-residue loss, in which, the mean loss penalizes the difference between the estimated age distribution's mean and the ground-truth age, whereas the residue loss penalizes the entropy of age probability out of dynamic top-K in the distribution. Experimental results in the datasets FG-NET and CLAP2016 have validated the effectiveness of the proposed loss.

Dataset

For FGNET, check the README, under FGNET folder.

For CLAP16, check the README, under CLAP folder.

Installation

  • Install python and pytorch
  Install PyTorch 1.7.1 + CUDA 10.1 
  Clone this repo.
  • Clone the repository
  git clone https://github.com/jacobzhaoziyuan/AMRLoss
  cd AMRLoss
  • Install dependencies
  pip install -r requirements.txt

Running

  cd scripts
  • For FGNET dataset
  bash FGNET_experiments.sh 
  • For CLAP2016 dataset
  bash CLAP_experiments.sh 

Citation

If you find the codebase useful for your research, please cite the paper:

@inproceedings{zhao2022adaptive,
  title={Adaptive Mean-Residue Loss for Robust Facial Age Estimation},
  author={Zhao, Ziyuan and Qian, Peisheng and Hou, Yubo and Zeng, Zeng},
  booktitle={2022 IEEE International Conference on Multimedia and Expo (ICME)},
  year={2022}
}

@misc{zhao2022adaptive,
    title={Adaptive Mean-Residue Loss for Robust Facial Age Estimation},
    author={Ziyuan Zhao and Peisheng Qian and Yubo Hou and Zeng Zeng},
    year={2022},
    eprint={2203.17156},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}

Acknowledgement

Part of the code is adapted from open-source codebase and original implementations of algorithms, we thank these authors for their fantastic and efficient codebase:

amr-loss's People

Contributors

jacobzhaoziyuan avatar

Watchers

 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.