ImageNetVC: Zero- and Few-Shot Visual Commonsense Evaluation on 1000 ImageNet Categories

Heming Xia, Qingxiu Dong, Lei Li, Jingjing Xu, Tianyu Liu, Ziwei Qin, Zhifang Sui

Abstract
Recently, Large Language Models (LLMs) have been serving as general-purpose interfaces, posing a significant demand for comprehensive visual knowledge. However, it remains unclear how well current LLMs and their visually augmented counterparts (VaLMs) can master visual commonsense knowledge. To investigate this, we propose ImageNetVC, a human-annotated dataset specifically designed for zero- and few-shot visual commonsense evaluation across 1,000 ImageNet categories. Utilizing ImageNetVC, we benchmark the fundamental visual commonsense knowledge of both unimodal LLMs and VaLMs. Furthermore, we analyze the factors affecting the visual commonsense knowledge of large-scale models, providing insights into the development of language models enriched with visual commonsense knowledge. Our code and dataset are available at https://github.com/hemingkx/ImageNetVC.
Anthology ID:
2023.findings-emnlp.133
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2009–2026
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.133
DOI:
10.18653/v1/2023.findings-emnlp.133
Bibkey:
Cite (ACL):
Heming Xia, Qingxiu Dong, Lei Li, Jingjing Xu, Tianyu Liu, Ziwei Qin, and Zhifang Sui. 2023. ImageNetVC: Zero- and Few-Shot Visual Commonsense Evaluation on 1000 ImageNet Categories. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 2009–2026, Singapore. Association for Computational Linguistics.
Cite (Informal):
ImageNetVC: Zero- and Few-Shot Visual Commonsense Evaluation on 1000 ImageNet Categories (Xia et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2023.findings-emnlp.133.pdf
PDF Search