Evaluating Attribute Comprehension in Large Vision-Language Models

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhang, Haiwen, Yang, Zixi, Liu, Yuanzhi, Wang, Xinran, He, Zheqi, Liang, Kongming, Ma, Zhanyu
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914923680890880
author Zhang, Haiwen
Yang, Zixi
Liu, Yuanzhi
Wang, Xinran
He, Zheqi
Liang, Kongming
Ma, Zhanyu
author_facet Zhang, Haiwen
Yang, Zixi
Liu, Yuanzhi
Wang, Xinran
He, Zheqi
Liang, Kongming
Ma, Zhanyu
contents Currently, large vision-language models have gained promising progress on many downstream tasks. However, they still suffer many challenges in fine-grained visual understanding tasks, such as object attribute comprehension. Besides, there have been growing efforts on the evaluations of large vision-language models, but lack of in-depth study of attribute comprehension and the visual language fine-tuning process. In this paper, we propose to evaluate the attribute comprehension ability of large vision-language models from two perspectives: attribute recognition and attribute hierarchy understanding. We evaluate three vision-language interactions, including visual question answering, image-text matching, and image-text cosine similarity. Furthermore, we explore the factors affecting attribute comprehension during fine-tuning. Through a series of quantitative and qualitative experiments, we introduce three main findings: (1) Large vision-language models possess good attribute recognition ability, but their hierarchical understanding ability is relatively limited. (2) Compared to ITC, ITM exhibits superior capability in capturing finer details, making it more suitable for attribute understanding tasks. (3) The attribute information in the captions used for fine-tuning plays a crucial role in attribute understanding. We hope this work can help guide future progress in fine-grained visual understanding of large vision-language models.
format Preprint
id arxiv_https___arxiv_org_abs_2408_13898
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Evaluating Attribute Comprehension in Large Vision-Language Models
Zhang, Haiwen
Yang, Zixi
Liu, Yuanzhi
Wang, Xinran
He, Zheqi
Liang, Kongming
Ma, Zhanyu
Computer Vision and Pattern Recognition
Currently, large vision-language models have gained promising progress on many downstream tasks. However, they still suffer many challenges in fine-grained visual understanding tasks, such as object attribute comprehension. Besides, there have been growing efforts on the evaluations of large vision-language models, but lack of in-depth study of attribute comprehension and the visual language fine-tuning process. In this paper, we propose to evaluate the attribute comprehension ability of large vision-language models from two perspectives: attribute recognition and attribute hierarchy understanding. We evaluate three vision-language interactions, including visual question answering, image-text matching, and image-text cosine similarity. Furthermore, we explore the factors affecting attribute comprehension during fine-tuning. Through a series of quantitative and qualitative experiments, we introduce three main findings: (1) Large vision-language models possess good attribute recognition ability, but their hierarchical understanding ability is relatively limited. (2) Compared to ITC, ITM exhibits superior capability in capturing finer details, making it more suitable for attribute understanding tasks. (3) The attribute information in the captions used for fine-tuning plays a crucial role in attribute understanding. We hope this work can help guide future progress in fine-grained visual understanding of large vision-language models.
title Evaluating Attribute Comprehension in Large Vision-Language Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.13898