Semi-supervised FusedGAN for Conditional Image Generation

We present FusedGAN, a deep network for conditional image synthesis with controllable sampling of diverse images. Fidelity, diversity and controllable sampling are the main quality measures of a good image generation model. Most existing models are insufficient in all three aspects. The FusedGAN can perform controllable sampling of diverse images with very high fidelity. We argue that controllability can be achieved by disentangling the generation process into various stages. In contrast to stacked GANs, where multiple stages of GANs are trained separately with full supervision of labeled intermediate images, the FusedGAN has a single stage pipeline with a built-in stacking of GANs. Unlike existing methods, which requires full supervision with paired conditions and images, the FusedGAN can effectively leverage more abundant images without corresponding conditions in training, to produce more diverse samples with high fidelity. We achieve this by fusing two generators: one for unconditional image generation, and the other for conditional image generation, where the two partly share a common latent space thereby disentangling the generation. We demonstrate the efficacy of the FusedGAN in fine grained image generation tasks such as text-to-image, and attribute-to-face generation.

[1]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Pietro Perona,et al.  The Caltech-UCSD Birds-200-2011 Dataset , 2011 .

[3]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[4]  Bernt Schiele,et al.  Learning Deep Representations of Fine-Grained Visual Descriptions , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Bernt Schiele,et al.  Generative Adversarial Text to Image Synthesis , 2016, ICML.

[6]  Alexei A. Efros,et al.  Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[7]  Alex Graves,et al.  DRAW: A Recurrent Neural Network For Image Generation , 2015, ICML.

[8]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[9]  Honglak Lee,et al.  Attribute2Image: Conditional Image Generation from Visual Attributes , 2015, ECCV.

[10]  Sanja Fidler,et al.  Be Your Own Prada: Fashion Synthesis with Structural Coherence , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[11]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[12]  Pietro Perona,et al.  Building a bird recognition app and large scale dataset with citizen scientists: The fine print in fine-grained dataset collection , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Sanja Fidler,et al.  Towards Diverse and Natural Image Descriptions via a Conditional GAN , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[14]  Abhinav Gupta,et al.  Generative Image Modeling Using Style and Structure Adversarial Networks , 2016, ECCV.

[15]  Dimitris N. Metaxas,et al.  StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[16]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[17]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[18]  Xiaogang Wang,et al.  Deep Learning Face Attributes in the Wild , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[19]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[20]  Bernt Schiele,et al.  Learning What and Where to Draw , 2016, NIPS.