PaliGemma：一个用于迁移的通用 3B 视觉语言模型
计算机视觉与模式识别
2024-10-11 v2 人工智能
计算与语言
机器学习
摘要
PaliGemma 是一个基于 SigLIP-So400m 视觉编码器和 Gemma-2B 语言模型的开放式视觉语言模型（Vision-Language Model, VLM）。它被训练为一个通用且广泛知识的基础模型，具备良好的迁移能力。在广泛的开放世界任务中表现出色。我们在近 40 个多样化任务上评估了 PaliGemma，包括标准 VLM 基准测试，以及更专业的任务，如遥感（remote-sensing）和分割（segmentation）。
引用
@article{arxiv.2407.07726,
title = {PaliGemma: A versatile 3B VLM for transfer},
author = {Lucas Beyer and Andreas Steiner and André Susano Pinto and Alexander Kolesnikov and Xiao Wang and Daniel Salz and Maxim Neumann and Ibrahim Alabdulmohsin and Michael Tschannen and Emanuele Bugliarello and Thomas Unterthiner and Daniel Keysers and Skanda Koppula and Fangyu Liu and Adam Grycner and Alexey Gritsenko and Neil Houlsby and Manoj Kumar and Keran Rong and Julian Eisenschlos and Rishabh Kabra and Matthias Bauer and Matko Bošnjak and Xi Chen and Matthias Minderer and Paul Voigtlaender and Ioana Bica and Ivana Balazevic and Joan Puigcerver and Pinelopi Papalampidi and Olivier Henaff and Xi Xiong and Radu Soricut and Jeremiah Harmsen and Xiaohua Zhai},
journal= {arXiv preprint arXiv:2407.07726},
year = {2024}
}
备注
v2 adds Appendix H and I and a few citations