面向视觉任务的视觉语言模型：一项综述
Vision-Language Models for Vision Tasks: A Survey
AI总结：
本文系统综述了视觉语言模型（VLMs）在视觉识别任务中的应用，涵盖其背景、基础架构、数据集、预训练与迁移方法及未来方向，旨在解决传统范式依赖众包标注且需逐任务训练的痛点。
摘要：
大多数视觉识别研究在深度神经网络（DNNs）训练中严重依赖众包标注数据，并且通常为每个单一视觉识别任务训练一个DNN，导致了一种费时费力的视觉识别范式。为了解决这两个挑战，视觉语言模型（VLMs）最近得到了深入研究，它从互联网上几乎无限可用的网络规模图文对中学习丰富的视觉语言关联，并使得单个VLM能够在各种视觉识别任务上进行零样本预测。本文对用于各种视觉识别任务的视觉语言模型进行了系统回顾，包括：(1) 介绍视觉识别范式发展的背景；(2) VLM的基础，总结了广泛采用的网络架构、预训练目标和下游任务；(3) VLM预训练和评估中广泛采用的数据集；(4) 对现有VLM预训练方法、VLM迁移学习方法和VLM知识蒸馏方法的回顾与分类；(5) 对所回顾方法的基准测试、分析与讨论；(6) 未来用于视觉识别的VLM研究中可追求的若干研究挑战和潜在研究方向。与此综述相关的项目已在 https://github.com/jingyi0000/VLM_survey 创建。
英文摘要：
Most visual recognition studies rely heavily on crowd-labelled data in deep neural networks (DNNs) training, and they usually train a DNN for each single visual recognition task, leading to a laborious and time-consuming visual recognition paradigm. To address the two challenges, Vision-Language Models (VLMs) have been intensively investigated recently, which learns rich vision-language correlation from web-scale image-text pairs that are almost infinitely available on the Internet and enables zero-shot predictions on various visual recognition tasks with a single VLM. This paper provides a systematic review of visual language models for various visual recognition tasks, including: (1) the background that introduces the development of visual recognition paradigms; (2) the foundations of VLM that summarize the widely-adopted network architectures, pre-training objectives, and downstream tasks; (3) the widely-adopted datasets in VLM pre-training and evaluations; (4) the review and categorization of existing VLM pre-training methods, VLM transfer learning methods, and VLM knowledge distillation methods; (5) the benchmarking, analysis and discussion of the reviewed methods; (6) several research challenges and potential research directions that could be pursued in the future VLM studies for visual recognition. A project associated with this survey has been created at https://github.com/jingyi0000/VLM_survey.
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。
