CAFE-GAN: Arbitrary Face Attribute Editing with Complementary Attention Feature
This work provides an incremental improvement for researchers and practitioners in computer vision working on face attribute editing, by reducing unintended changes in generated images.
This paper addresses the problem of unintended alterations in face attribute editing by proposing CAFE-GAN, a novel GAN model that uses Complementary Attention Features (CAFE) to identify and edit only the relevant facial regions. CAFE considers both target and complementary attributes to guide the editing process, resulting in more precise attribute manipulation.
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.