Visual Commonsense in Pretrained Unimodal and Multimodal Models

Chenyu Zhang, Benjamin Van Durme, Zhuowan Li, Elias Stengel-Eskin


Abstract
Our commonsense knowledge about objects includes their typical visual attributes; we know that bananas are typically yellow or green, and not purple. Text and image corpora, being subject to reporting bias, represent this world-knowledge to varying degrees of faithfulness. In this paper, we investigate to what degree unimodal (language-only) and multimodal (image and language) models capture a broad range of visually salient attributes. To that end, we create the Visual Commonsense Tests (ViComTe) dataset covering 5 property types (color, shape, material, size, and visual co-occurrence) for over 5000 subjects. We validate this dataset by showing that our grounded color data correlates much better than ungrounded text-only data with crowdsourced color judgments provided by Paik et al. (2021). We then use our dataset to evaluate pretrained unimodal models and multimodal models. Our results indicate that multimodal models better reconstruct attribute distributions, but are still subject to reporting bias. Moreover, increasing model size does not enhance performance, suggesting that the key to visual commonsense lies in the data.
Anthology ID:
2022.naacl-main.390
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5321–5335
Language:
URL:
https://aclanthology.org/2022.naacl-main.390
DOI:
10.18653/v1/2022.naacl-main.390
Bibkey:
Cite (ACL):
Chenyu Zhang, Benjamin Van Durme, Zhuowan Li, and Elias Stengel-Eskin. 2022. Visual Commonsense in Pretrained Unimodal and Multimodal Models. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5321–5335, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Visual Commonsense in Pretrained Unimodal and Multimodal Models (Zhang et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.390.pdf
Video:
 https://aclanthology.org/2022.naacl-main.390.mp4
Code
 chenyuheidizhang/vl-commonsense
Data
CoDaVisual Genome