Panther: Illuminate the Sight of Multimodal LLMs with Instruction-Guided Visual Prompts

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Honglin, Gao, Yuting, Zhu, Chenglu, Chen, Jingdong, Yang, Ming, Yang, Lin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912129992359936
author Li, Honglin
Gao, Yuting
Zhu, Chenglu
Chen, Jingdong
Yang, Ming
Yang, Lin
author_facet Li, Honglin
Gao, Yuting
Zhu, Chenglu
Chen, Jingdong
Yang, Ming
Yang, Lin
contents Multimodal large language models (MLLMs) are closing the gap to human visual perception capability rapidly, while, still lag behind on attending to subtle images details or locating small objects precisely, etc. Common schemes to tackle these issues include deploying multiple vision encoders or operating on original high-resolution images. Few studies have concentrated on taking the textual instruction into improving visual representation, resulting in losing focus in some vision-centric tasks, a phenomenon we herein termed as Amblyopia. In this work, we introduce Panther, a MLLM that closely adheres to user instruction and locates targets of interests precisely, with the finesse of a black panther. Specifically, Panther comprises three integral components: Panther-VE, Panther-Bridge, and Panther-Decoder. Panther-VE integrates user instruction information at the early stages of the vision encoder, thereby extracting the most relevant and useful visual representations. The Panther-Bridge module, equipped with powerful filtering capabilities, significantly reduces redundant visual information, leading to a substantial savings in training costs. The Panther-Decoder is versatile and can be employed with any decoder-only architecture of LLMs without discrimination. Experimental results, particularly on vision-centric benchmarks, have demonstrated the effectiveness of Panther.
format Preprint
id arxiv_https___arxiv_org_abs_2411_13909
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Panther: Illuminate the Sight of Multimodal LLMs with Instruction-Guided Visual Prompts
Li, Honglin
Gao, Yuting
Zhu, Chenglu
Chen, Jingdong
Yang, Ming
Yang, Lin
Computer Vision and Pattern Recognition
Multimodal large language models (MLLMs) are closing the gap to human visual perception capability rapidly, while, still lag behind on attending to subtle images details or locating small objects precisely, etc. Common schemes to tackle these issues include deploying multiple vision encoders or operating on original high-resolution images. Few studies have concentrated on taking the textual instruction into improving visual representation, resulting in losing focus in some vision-centric tasks, a phenomenon we herein termed as Amblyopia. In this work, we introduce Panther, a MLLM that closely adheres to user instruction and locates targets of interests precisely, with the finesse of a black panther. Specifically, Panther comprises three integral components: Panther-VE, Panther-Bridge, and Panther-Decoder. Panther-VE integrates user instruction information at the early stages of the vision encoder, thereby extracting the most relevant and useful visual representations. The Panther-Bridge module, equipped with powerful filtering capabilities, significantly reduces redundant visual information, leading to a substantial savings in training costs. The Panther-Decoder is versatile and can be employed with any decoder-only architecture of LLMs without discrimination. Experimental results, particularly on vision-centric benchmarks, have demonstrated the effectiveness of Panther.
title Panther: Illuminate the Sight of Multimodal LLMs with Instruction-Guided Visual Prompts
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.13909