Skip to content

[IJCAI18] SSR-Net: A Compact Soft Stagewise Regression Network for Age Estimation

Notifications You must be signed in to change notification settings

muneeb991/SSR-Net_megaage-asian

This branch is up to date with b02901145/SSR-Net_megaage-asian:master.

Folders and files

NameName
Last commit message
Last commit date

Latest commit

0708992 · Aug 6, 2018

History

36 Commits
Aug 6, 2018
Aug 6, 2018
Aug 6, 2018
Aug 6, 2018
Aug 6, 2018
Aug 6, 2018
Aug 6, 2018
Aug 6, 2018
Aug 6, 2018
Aug 6, 2018
Aug 6, 2018
Aug 6, 2018

Repository files navigation

SSR-Net_megaage-asian

[IJCAI18] SSR-Net: A Compact Soft Stagewise Regression Network for Age Estimation

Last update: 2018/08/06 (Adding MegaAge-Asian dataset.)

Paper

PDF

https://github.com/shamangary/SSR-Net/blob/master/ijcai18_ssrnet_pdfa_2b.pdf

Authors

Tsun-Yi Yang, Yi-Husan Huang, Yen-Yu Lin, Pi-Cheng Hsiu, and Yung-Yu Chuang

Abstract

This paper presents a novel CNN model called Soft Stagewise Regression Network (SSR-Net) for age estimation from a single image with a compact model size. Inspired by DEX, we address age estimation by performing multi-class classification and then turning classification results into regression by calculating the expected values. SSR-Net takes a coarse-to-fine strategy and performs multi-class classification with multiple stages. Each stage is only responsible for refining the decision of the previous stage. Thus, each stage performs a task with few classes and requires few neurons, greatly reducing the model size. For addressing the quantization issue introduced by grouping ages into classes, SSR-Net assigns a dynamic range to each age class by allowing it to be shifted and scaled according to the input face image. Both the multi-stage strategy and the dynamic range are incorporated into the formulation of soft stagewise regression. A novel network architecture is proposed for carrying out soft stagewise regression. The resultant SSR-Net model is very compact and takes only 0.32 MB. Despite of its compact size, SSR-Net’s performance approaches those of the state-of-the-art methods whose model sizes are more than 1500x larger.

Platform

  • Keras
  • Tensorflow
  • GTX-1080Ti and GTX-1080
  • Ubuntu

Codes

This repository is for MegaAge-Asian datasets. There are three different section of this project.

  • Data pre-processing
  • Training
  • Testing

We will go through the details in the following sections.

Data pre-processing

python TYY_Megaage_asian_create_db.py

Training

  • For SSR-Net
bash run_ssrnet_megaage.sh
  • For MobileNet
bash run_megaage_MobileNet.sh
  • For DenseNet
bash run_megaage_DenseNet.sh

Testing

Create predicted results and calculate CA (cumulative accuracy)

  • For SSR-Net, MobileNet and DenseNet
bash run_CA.sh

About

[IJCAI18] SSR-Net: A Compact Soft Stagewise Regression Network for Age Estimation

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 99.3%
  • Shell 0.7%