ANNA: Abstractive Text-to-Image Synthesis with Filtered News Captions
This work addresses a domain-specific challenge in generating images from abstractive news captions, but it is incremental as it primarily benchmarks existing methods on a new dataset.
The paper tackles the problem of text-to-image synthesis for abstractive news captions, which are not directly descriptive, by introducing the ANNA dataset and benchmarking existing models, showing that transfer learning achieves limited success in understanding these captions.
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 .