Enregistré dans:
Détails bibliographiques
Auteurs principaux: Liu, Yuan, Tian, Le, Zhou, Xiao, Zhou, Jie
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2405.11850
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929348820336640
author Liu, Yuan
Tian, Le
Zhou, Xiao
Zhou, Jie
author_facet Liu, Yuan
Tian, Le
Zhou, Xiao
Zhou, Jie
contents Recent advancements in large vision-language models (LVLMs), such as GPT4-V and LLaVA, have been substantial. LLaVA's modular architecture, in particular, offers a blend of simplicity and efficiency. Recent works mainly focus on introducing more pre-training and instruction tuning data to improve model's performance. This paper delves into the often-neglected aspects of data efficiency during pre-training and the selection process for instruction tuning datasets. Our research indicates that merely increasing the size of pre-training data does not guarantee improved performance and may, in fact, lead to its degradation. Furthermore, we have established a pipeline to pinpoint the most efficient instruction tuning (SFT) dataset, implying that not all SFT data utilized in existing studies are necessary. The primary objective of this paper is not to introduce a state-of-the-art model, but rather to serve as a roadmap for future research, aiming to optimize data usage during pre-training and fine-tuning processes to enhance the performance of vision-language models.
format Preprint
id arxiv_https___arxiv_org_abs_2405_11850
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Rethinking Overlooked Aspects in Vision-Language Models
Liu, Yuan
Tian, Le
Zhou, Xiao
Zhou, Jie
Computer Vision and Pattern Recognition
Recent advancements in large vision-language models (LVLMs), such as GPT4-V and LLaVA, have been substantial. LLaVA's modular architecture, in particular, offers a blend of simplicity and efficiency. Recent works mainly focus on introducing more pre-training and instruction tuning data to improve model's performance. This paper delves into the often-neglected aspects of data efficiency during pre-training and the selection process for instruction tuning datasets. Our research indicates that merely increasing the size of pre-training data does not guarantee improved performance and may, in fact, lead to its degradation. Furthermore, we have established a pipeline to pinpoint the most efficient instruction tuning (SFT) dataset, implying that not all SFT data utilized in existing studies are necessary. The primary objective of this paper is not to introduce a state-of-the-art model, but rather to serve as a roadmap for future research, aiming to optimize data usage during pre-training and fine-tuning processes to enhance the performance of vision-language models.
title Rethinking Overlooked Aspects in Vision-Language Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.11850