Logo image
Back
CAFE-GAN: Arbitrary Face Attribute Editing with Complementary Attention Feature
Book chapter   Open access   Peer reviewed

CAFE-GAN: Arbitrary Face Attribute Editing with Complementary Attention Feature

Jeong-gi Kwak, David K. Han and Hanseok Ko
Computer Vision – ECCV 2020, pp 524-540
13 Nov 2020
DOI: https://doi.org/10.1007/978-3-030-58568-6_31
url
https://arxiv.org/pdf/2011.11900View
Open

Abstract

Complementary attention feature Complementary feature matching Face attribute editing GAN
The goal of face attribute editing is altering a facial image according to given target attributes such as hair color, mustache, gender, etc. It belongs to the image-to-image domain transfer problem with a set of attributes considered as a distinctive domain. There have been some works in multi-domain transfer problem focusing on facial attribute editing employing Generative Adversarial Network (GAN). These methods have reported some successes but they also result in unintended changes in facial regions - meaning the generator alters regions unrelated to the specified attributes. To address this unintended altering problem, we propose a novel GAN model which is designed to edit only the parts of a face pertinent to the target attributes by the concept of Complementary Attention Feature (CAFE). CAFE identifies the facial regions to be transformed by considering both target attributes as well as “complementary attributes”, which we define as those attributes absent in the input facial image. In addition, we introduce a complementary feature matching to help in training the generator for utilizing the spatial information of attributes. Effectiveness of the proposed method is demonstrated by analysis and comparison study with state-of-the-art methods.

Metrics

6 Record Views
19 citations in Scopus

Details

Logo image