Inducing Optimal Attribute Representations for Conditional GANs

by   Binod Bhattarai, et al.

Conditional GANs are widely used in translating an image from one category to another. Meaningful conditions to GANs provide greater flexibility and control over the nature of the target domain synthetic data. Existing conditional GANs commonly encode target domain label information as hard-coded categorical vectors in the form of 0s and 1s. The major drawbacks of such representations are inability to encode the high-order semantic information of target categories and their relative dependencies. We propose a novel end-to-end learning framework with Graph Convolutional Networks to learn the attribute representations to condition on the generator. The GAN losses, i.e. the discriminator and attribute classification losses, are fed back to the Graph resulting in the synthetic images that are more natural and clearer in attributes. Moreover, prior-arts are given priorities to condition on the generator side, not on the discriminator side of GANs. We apply the conditions to the discriminator side as well via multi-task learning. We enhanced the four state-of-the art cGANs architectures: Stargan, Stargan-JNT, AttGAN and STGAN. Our extensive qualitative and quantitative evaluations on challenging face attributes manipulation data set, CelebA, LFWA, and RaFD, show that the cGANs enhanced by our methods outperform by a large margin, compared to their counter-parts and other conditioning methods, in terms of both target attributes recognition rates and quality measures such as PSNR and SSIM.


page 1

page 13

page 14

page 18

page 19

page 21

page 22

page 23


Enhanced 3DMM Attribute Control via Synthetic Dataset Creation Pipeline

While facial attribute manipulation of 2D images via Generative Adversar...

Guiding GANs: How to control non-conditional pre-trained GANs for conditional image generation

Generative Adversarial Networks (GANs) are an arrange of two neural netw...

Enhancing the Input Representation: From Complexity to Simplicity

We introduce an efficient algorithm for mining informative combinations ...

cGANs with Projection Discriminator

We propose a novel, projection based way to incorporate the conditional ...

SMILE: Semantically-guided Multi-attribute Image and Layout Editing

Attribute image manipulation has been a very active topic since the intr...

Label Geometry Aware Discriminator for Conditional Generative Networks

Multi-domain image-to-image translation with conditional Generative Adve...

Please sign up or login with your details

Forgot password? Click here to reset