TAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Network
Published in
arXiv.org(2017)External Links:
TL
TL;DR
The TAC-GAN model is trained on the Oxford-102 dataset of flowers, and the discriminability of the generated images with Inception-Score, as well as their diversity using the Multi-Scale Structural Similarity Index (MS-SSIM).
Abstract
In this work, we present the Text Conditioned Auxiliary Classifier Generative Adversarial Network, (TAC-GAN) a text to image Generative Adversarial Network (GAN) for synthesizing images from their text descriptions. Former approaches have tried to condition the generative process on the textual data; but allying it to the usage of class information, known to diversify the generated samples and improve their structural coherence, has not been explored. We trained the presented TAC-GAN model on the Oxford-102 dataset of flowers, and evaluated the discriminability of the generated images with Inception-Score, as well as their diversity using the Multi-Scale Structural Similarity Index (MS-SSIM). Our approach outperforms the state-of-the-art models, i.e., its inception score is 3.45, corresponding to a relative increase of 7.8% compared to the recently introduced StackGan. A comparison of the mean MS-SSIM scores of the training and generated samples per class shows that our approach is able to generate highly diverse images with an average MS-SSIM of 0.14 over all generated classes.
References28 items
1
Learning from Simulated and Unsupervised Images through Adversarial Training
2
StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks
3
Image-to-Image Translation with Conditional Adversarial Networks
4
Conditional Image Synthesis with Auxiliary Classifier GANs
5