We propose Strongly Supervised pre-training with ScreenShots (S4) - a novel pre-training paradigm for Vision-Language Models using data from large-scale web screenshot rendering. Using web screenshots unlocks a treasure trove of visual and textual cues that are not present in using image-text pairs. In S4, we leverage the inherent tree-structured hierarchy of HTML elements and the spatial localization to carefully design 10 pre-training tasks with large scale annotated data. These tasks resemble downstream tasks across different domains and the annotations are cheap to obtain. We demonstrate that, compared to current screenshot pre-training objectives, our innovative pre-training method significantly enhances performance of image-to-text model in nine varied and popular downstream tasks - up to 76.1% improvements on Table Detection, and at least 1% on Widget Captioning.
@article{arxiv.2403.03346,
title = {Enhancing Vision-Language Pre-training with Rich Supervisions},
author = {Yuan Gao and Kunyu Shi and Pengkai Zhu and Edouard Belval and Oren Nuriel and Srikar Appalaraju and Shabnam Ghadar and Vijay Mahadevan and Zhuowen Tu and Stefano Soatto},
journal= {arXiv preprint arXiv:2403.03346},
year = {2025}
}