Improving Text to Image Generation using Mode-seeking Function

TL;DR

This paper introduces a mode-seeking loss function to improve text-to-image GANs, effectively reducing mode collapse and enhancing diversity in generated images, validated on CUB and COCO datasets.

Contribution

The paper proposes a novel mode-seeking loss function specifically designed for text-to-image GANs to mitigate mode collapse and improve output diversity.

Findings

Enhanced image diversity compared to baseline models

Effective reduction of mode collapse in GAN training

Validated improvements on CUB and COCO datasets

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.