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

TL;DR

This paper introduces CAFE-GAN, a novel face attribute editing model that precisely alters only relevant facial regions by leveraging complementary attention features, improving editing accuracy and reducing unintended changes.

Contribution

The paper proposes a new GAN model utilizing Complementary Attention Features to focus edits on pertinent facial regions based on target and absent attributes.

Findings

CAFE-GAN achieves more accurate attribute editing.

Reduces unintended facial region alterations.

Outperforms state-of-the-art methods in experiments.

Abstract

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.