to download project base paper vision language model.


Most visual recognition studies rely heavily on crowd-labeled data in deep neural networks (DNNs) training, and they usually train a DNN for each single vision language model 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, They learn rich vision-language correlation from web-scale image-text pairs that are almost infinitely available on the Internet and enable 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

 ,VISION-LANGUAGE MODELS FOR VISION TASKS: A SURVEY,  fiinal year projects, vision language model
Leave a Comment


No comments yet. Why don’t you start the discussion?

Leave a Reply

Your email address will not be published. Required fields are marked *