Saved in:
Bibliographic Details
Main Authors: Zhu, Lei, Wei, Fangyun, Lu, Yanye
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.07874
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914711116709888
author Zhu, Lei
Wei, Fangyun
Lu, Yanye
author_facet Zhu, Lei
Wei, Fangyun
Lu, Yanye
contents In this work, we investigate the potential of a large language model (LLM) to directly comprehend visual signals without the necessity of fine-tuning on multi-modal datasets. The foundational concept of our method views an image as a linguistic entity, and translates it to a set of discrete words derived from the LLM's vocabulary. To achieve this, we present the Vision-to-Language Tokenizer, abbreviated as V2T Tokenizer, which transforms an image into a ``foreign language'' with the combined aid of an encoder-decoder, the LLM vocabulary, and a CLIP model. With this innovative image encoding, the LLM gains the ability not only for visual comprehension but also for image denoising and restoration in an auto-regressive fashion-crucially, without any fine-tuning. We undertake rigorous experiments to validate our method, encompassing understanding tasks like image recognition, image captioning, and visual question answering, as well as image denoising tasks like inpainting, outpainting, deblurring, and shift restoration. Code and models are available at https://github.com/zh460045050/V2L-Tokenizer.
format Preprint
id arxiv_https___arxiv_org_abs_2403_07874
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Beyond Text: Frozen Large Language Models in Visual Signal Comprehension
Zhu, Lei
Wei, Fangyun
Lu, Yanye
Computer Vision and Pattern Recognition
In this work, we investigate the potential of a large language model (LLM) to directly comprehend visual signals without the necessity of fine-tuning on multi-modal datasets. The foundational concept of our method views an image as a linguistic entity, and translates it to a set of discrete words derived from the LLM's vocabulary. To achieve this, we present the Vision-to-Language Tokenizer, abbreviated as V2T Tokenizer, which transforms an image into a ``foreign language'' with the combined aid of an encoder-decoder, the LLM vocabulary, and a CLIP model. With this innovative image encoding, the LLM gains the ability not only for visual comprehension but also for image denoising and restoration in an auto-regressive fashion-crucially, without any fine-tuning. We undertake rigorous experiments to validate our method, encompassing understanding tasks like image recognition, image captioning, and visual question answering, as well as image denoising tasks like inpainting, outpainting, deblurring, and shift restoration. Code and models are available at https://github.com/zh460045050/V2L-Tokenizer.
title Beyond Text: Frozen Large Language Models in Visual Signal Comprehension
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.07874