Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

6-2021

Abstract

Generative adversarial networks (GANs) learn to map noise latent vectors to high- fidelity image outputs. It is found that the input latent space shows semantic correlations with the output image space. Recent works aim to interpret the latent space and discover meaningful directions that correspond to human interpretable image transformations. However, these methods either rely on explicit scores of attributes (e.g., memorability) or are restricted to binary ones (e.g., gender), which largely limits the applicability of editing tasks, especially for free- form artistic tasks like style/anime editing. In this paper, we propose an adversarial method, AdvStyle, for discovering interpretable directions in the absence of well- labeled scores or binary attributes. In particular, the proposed adversarial method simultaneously optimizes the discovered directions and the attribute assessor using the target attribute data as positive samples, while the generated ones being negative. In this way, arbitrary attributes can be edited by collecting positive data only, and the proposed method learns a controllable representation enabling manipulation of non- binary attributes like anime styles and facial characteristics. Moreover, the proposed learning strategy attenuates the entanglement between attributes, such that multi-attribute manipulation can be easily achieved without any additional constraint. Furthermore, we reveal several interesting semantics with the involuntarily learned negative directions. Extensive experiments on 9 anime attributes and 7 human attributes demonstrate the effectiveness of our adversarial approach qualitatively and quantitatively

Keywords

Attribute data, Binary attributes, Freeforms, High-fidelity images, Image space, Image transformations, Latent vectors, Learn+, Positive data, Space directions

Discipline

Databases and Information Systems

Research Areas

Information Systems and Management

Publication

Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Virtual, Online, June 19-25

First Page

12172

Last Page

12180

ISBN

9781665445092

Identifier

10.1109/CVPR46437.2021.01200

Publisher

IEEE

City or Country

New Jersey

Additional URL

https://doi.org/10.1109/CVPR46437.2021.01200

Download

Share

COinS