This paper presents PaLI-3, a smaller, faster, and stronger vision language model (VLM) that compares favorably to similar models that are 10x larger. As part of arriving at this strong performance, we compare Vision Transformer (ViT) models pretrained using classification objectives to contrastively (SigLIP) pretrained ones. We find that, while slightly underperforming on standard image classification benchmarks, SigLIP-based PaLI shows superior performance across various multimodal benchmarks, especially on localization and visually-situated text understanding. We scale the SigLIP image encoder up to 2 billion parameters, and achieves a new state-of-the-art on multilingual cross-modal retrieval. We hope that PaLI-3, at only 5B parameters, rekindles research on fundamental pieces of complex VLMs, and could fuel a new generation of scaled-up models.
@article{arxiv.2310.09199,
title = {PaLI-3 Vision Language Models: Smaller, Faster, Stronger},
author = {Xi Chen and Xiao Wang and Lucas Beyer and Alexander Kolesnikov and Jialin Wu and Paul Voigtlaender and Basil Mustafa and Sebastian Goodman and Ibrahim Alabdulmohsin and Piotr Padlewski and Daniel Salz and Xi Xiong and Daniel Vlasic and Filip Pavetic and Keran Rong and Tianli Yu and Daniel Keysers and Xiaohua Zhai and Radu Soricut},
journal= {arXiv preprint arXiv:2310.09199},
year = {2023}
}