LAVIS：一个面向视觉智能的图书馆
LAVIS: A Library for Language-Vision Intelligence
摘要：
我们介绍LAVIS，一个开源的深度学习库，用于LANGUage-VISion研究和应用。LAVIS旨在成为一站式综合图书馆，为研究人员和从业人员提供语言视觉领域的最新进展，以及未来的研究和开发。它具有统一的界面，可以轻松访问最先进的图像语言，视频语言模型和常见的数据集。LAVIS支持各种任务的培训、评估和基准测试，包括多模态分类、检索、字幕、视觉问答、对话和预培训。同时，该库还具有高度的可扩展性和可配置性，便于未来的开发和定制。在这份技术报告中，我们描述了库的设计原则、关键组件和功能，并介绍了常见语言视觉任务的基准测试结果。该库可在https://github.com/salesforce/LAVIS上获得。
英文摘要：
We introduce LAVIS, an open-source deep learning library for LAnguage-VISion research and applications. LAVIS aims to serve as a one-stop comprehensive library that brings recent advancements in the language-vision field accessible for researchers and practitioners, as well as fertilizing future research and development. It features a unified interface to easily access state-of-the-art image-language, video-language models and common datasets. LAVIS supports training, evaluation and benchmarking on a rich variety of tasks, including multimodal classification, retrieval, captioning, visual question answering, dialogue and pre-training. In the meantime, the library is also highly extensible and configurable, facilitating future development and customization. In this technical report, we describe design principles, key components and functionalities of the library, and also present benchmarking results across common language-vision tasks. The library is available at: https://github.com/salesforce/LAVIS.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
