TAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Network

TL;DR

This paper introduces TAC-GAN, a novel text-to-image GAN that incorporates class information to enhance image diversity and structural coherence, outperforming previous models on the Oxford-102 flowers dataset.

Contribution

The paper presents TAC-GAN, a new model that combines text conditioning with class information for improved image synthesis from text descriptions.

Findings

Inception score of 3.45, 7.8% higher than StackGAN

High diversity in generated images with average MS-SSIM of 0.14

Outperforms state-of-the-art models on Oxford-102 dataset

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.