ANNA: Abstractive Text-to-Image Synthesis with Filtered News Captions

TL;DR

This paper introduces ANNA, a new dataset of abstractive news captions for evaluating Text-to-Image synthesis models in news domains, highlighting challenges in understanding complex, context-rich captions.

Contribution

The paper presents ANNA, a novel dataset of abstractive news captions, and benchmarks current Text-to-Image models, revealing limitations in handling complex contextual information.

Findings

Transfer learning shows limited success in understanding abstractive captions.

Current models struggle to learn relationships between content and context.

ANNA dataset exposes challenges in news domain image synthesis.

Abstract

Advancements in Text-to-Image synthesis over recent years have focused more on improving the quality of generated samples using datasets with descriptive prompts. However, real-world image-caption pairs present in domains such as news data do not use simple and directly descriptive captions. With captions containing information on both the image content and underlying contextual cues, they become abstractive in nature. In this paper, we launch ANNA, an Abstractive News captioNs dAtaset extracted from online news articles in a variety of different contexts. We explore the capabilities of current Text-to-Image synthesis models to generate news domain-specific images using abstractive captions by benchmarking them on ANNA, in both standard training and transfer learning settings. The generated images are judged on the basis of contextual relevance, visual quality, and perceptual similarity to ground-truth image-caption pairs. Through our experiments, we show that techniques such as transfer learning achieve limited success in understanding abstractive captions but still fail to consistently learn the relationships between content and context features. The Dataset is available at https://github.com/aashish2000/ANNA .