Saved in:
Bibliographic Details
Main Authors: Li, Binzhe, Wang, Shurun, Wang, Shiqi, Ye, Yan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.17060
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916335001272320
author Li, Binzhe
Wang, Shurun
Wang, Shiqi
Ye, Yan
author_facet Li, Binzhe
Wang, Shurun
Wang, Shiqi
Ye, Yan
contents In recent years, large visual language models (LVLMs) have shown impressive performance and promising generalization capability in multi-modal tasks, thus replacing humans as receivers of visual information in various application scenarios. In this paper, we pioneer to propose a variable bitrate image compression framework consisting of a pre-editing module and an end-to-end codec to achieve promising rate-accuracy performance for different LVLMs. In particular, instead of optimizing an adaptive pre-editing network towards a particular task or several representative tasks, we propose a new optimization strategy tailored for LVLMs, which is designed based on the representation and discrimination capability with token-level distortion and rank. The pre-editing module and the variable bitrate end-to-end image codec are jointly trained by the losses based on semantic tokens of the large model, which introduce enhanced generalization capability for various data and tasks. {Experimental results demonstrate that the proposed framework could efficiently achieve much better rate-accuracy performance compared to the state-of-the-art coding standard, Versatile Video Coding.} Meanwhile, experiments with multi-modal tasks have revealed the robustness and generalization capability of the proposed framework.
format Preprint
id arxiv_https___arxiv_org_abs_2407_17060
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle High Efficiency Image Compression for Large Visual-Language Models
Li, Binzhe
Wang, Shurun
Wang, Shiqi
Ye, Yan
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Image and Video Processing
In recent years, large visual language models (LVLMs) have shown impressive performance and promising generalization capability in multi-modal tasks, thus replacing humans as receivers of visual information in various application scenarios. In this paper, we pioneer to propose a variable bitrate image compression framework consisting of a pre-editing module and an end-to-end codec to achieve promising rate-accuracy performance for different LVLMs. In particular, instead of optimizing an adaptive pre-editing network towards a particular task or several representative tasks, we propose a new optimization strategy tailored for LVLMs, which is designed based on the representation and discrimination capability with token-level distortion and rank. The pre-editing module and the variable bitrate end-to-end image codec are jointly trained by the losses based on semantic tokens of the large model, which introduce enhanced generalization capability for various data and tasks. {Experimental results demonstrate that the proposed framework could efficiently achieve much better rate-accuracy performance compared to the state-of-the-art coding standard, Versatile Video Coding.} Meanwhile, experiments with multi-modal tasks have revealed the robustness and generalization capability of the proposed framework.
title High Efficiency Image Compression for Large Visual-Language Models
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Image and Video Processing
url https://arxiv.org/abs/2407.17060