Generative Attribute Controller with Conditional Filtered Generative Adversarial Networks
Authors:
- Takuhiro KanekoTKTakuhiro Kaneko
- Kaoru HiramatsuKHKaoru Hiramatsu
- Kunio KashinoKKKunio Kashino
- 1 July 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 7006-7015
Abstract
We present a generative attribute controller (GAC), a novel functionality for generating or editing an image while intuitively controlling large variations of an attribute. This controller is based on a novel generative model called the conditional filtered generative adversarial network (CFGAN), which is an extension of the conventional conditional GAN (CGAN) that incorporates a filtering architecture into the generator input. Unlike the conventional CGAN, which represents an attribute directly using an observable variable (e.g., the binary indicator of attribute presence) so its controllability is restricted to attribute labeling (e.g., restricted to an ON or OFF control), the CFGAN has a filtering architecture that associates an attribute with a multi-dimensional latent variable, enabling latent variations of the attribute to be represented. We also define the filtering architecture and training scheme considering controllability, enabling the variations of the attribute to be intuitively controlled using typical controllers (radio buttons and slide bars). We evaluated our CFGAN on MNIST, CUB, and CelebA datasets and show that it enables large variations of an attribute to be not only represented but also intuitively controlled while retaining identity. We also show that the learned latent space has enough expressive power to conduct attribute transfer and attribute-based image retrieval.Keywords
This publication has 19 references indexed in Scilit:
- Learning to generate chairs with convolutional neural networks2015
- Illumination-Aware Age Progression2014
- Expression flow for 3D-aware face component transfer2011
- PatchMatchACM Transactions on Graphics, 2009
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006
- A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 2006
- Colorization using optimizationACM Transactions on Graphics, 2004
- Color transfer between imagesIEEE Computer Graphics and Applications, 2001
- As-rigid-as-possible shape interpolation2000
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998