Improving Text to Image Generation using Mode-seeking Function
arXiv:2008.08976
Abstract
Generative Adversarial Networks (GANs) have long been used to understand the semantic relationship between the text and image. However, there are problems with mode collapsing in the image generation that causes some preferred output modes. Our aim is to improve the training of the network by using a specialized mode-seeking loss function to avoid this issue. In the text to image synthesis, our loss function differentiates two points in latent space for the generation of distinct images. We validate our model on the Caltech Birds (CUB) dataset and the Microsoft COCO dataset by changing the intensity of the loss function during the training. Experimental results demonstrate that our model works very well compared to some state-of-the-art approaches.
changes : changed the title of the research for submission to CVIU
References in corpus (9)
- Auto-Encoding Variational Bayes
- Conditional Generative Adversarial Nets
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Unrolled Generative Adversarial Networks
- Mode Regularized Generative Adversarial Networks
- Learning What and Where to Draw
- Semantic Object Accuracy for Generative Text-to-Image Synthesis
- Diversity-Sensitive Conditional Generative Adversarial Networks
- TAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Network