Augmenting RetinaFace Model with Conditional Generative Adversarial Networks for Hair Segmentation

Zhuojun Yu, Ka Cheng Choi

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)

Abstract

In this paper, an augmentation of the RetinaFace model for hair segmentation is proposed by incorporating a Conditional Generative Adversarial Network (cGAN). The proposed model is trained to generate high-quality hair segmentation masks by considering various hair textures, colors, and styles. Our approach is based on the idea that hair segmentation can benefit from the use of cGANs, because they can learn to generate realistic hair images and help improve the performance of RetinaFace. Experimental results show that our model outperforms the RetinaFace model on several benchmarks, achieving state-of-the-art performance.

Original languageEnglish
Title of host publication2023 6th International Conference on Artificial Intelligence and Big Data, ICAIBD 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages890-894
Number of pages5
ISBN (Electronic)9781665491259
DOIs
Publication statusPublished - 2023
Event6th International Conference on Artificial Intelligence and Big Data, ICAIBD 2023 - Chengdu, China
Duration: 26 May 202329 May 2023

Publication series

Name2023 6th International Conference on Artificial Intelligence and Big Data, ICAIBD 2023

Conference

Conference6th International Conference on Artificial Intelligence and Big Data, ICAIBD 2023
Country/TerritoryChina
CityChengdu
Period26/05/2329/05/23

Keywords

  • RetinaFace model
  • conditional generative adversarial network (cGAN)
  • convolutional neural networks (CNNs)
  • deep learning models
  • face detection
  • hair segmentation

Fingerprint

Dive into the research topics of 'Augmenting RetinaFace Model with Conditional Generative Adversarial Networks for Hair Segmentation'. Together they form a unique fingerprint.

Cite this