Visual Commonsense in Pretrained Unimodal and Multimodal Models

By Benjamin Van Durme, Zhuowan Li, Elias Stengel-Eskin. 2022

45 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition, Experimental and Cognitive Psychology, Multimodal Learning, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Jianfeng Gao
2. Furu Wei
3. Yejin Choi
4. Luc Van Gool
5. Li Dong
6. Dacheng Tao
7. Trevor Darrell
8. Mohit Bansal

In Experimental and Cognitive Psychology

1. Yejin Choi
2. Daniel Fried

In Multimodal Learning

1. Jianfeng Gao
2. Li Dong
3. Furu Wei
4. Yejin Choi
5. Haoyu Song
6. Ronan Le Bras
7. Daniel Fried
8. Zhe Gan

In Representation & Self-Supervised Learning

1. Xiaodong Liu
2. Jianfeng Gao
3. Li Dong
4. Yejin Choi
5. Maarten Sap
6. Ronan Le Bras
7. Daniel Fried
8. Hao Cheng

Citations in the corpus

• Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs (2022, methodology): “…language models, but we focus on accessing GPT-3 (Brown et al., 2020) through an API, since we do not have access to some of the larger models out there (PaLM; Chowdhery et al., 2022) nor do we have the computational resources to run an open-source version of GPT-3 (OPT; Zhang et al., 2022b).”
• Visually-Augmented Language Modeling (2022, methodology): “We evaluate the OPT (1.3B parameters) (Zhang et al., 2022b) model on these visual–knowledge-intensive tasks and the results are presented in Table 8.”