Visual Commonsense in Pretrained Unimodal and Multimodal Models
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 automatically extract a visually-grounded commonsense 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 pre-trained unimodal models and multimodal models. Our results show 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.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeWorld KnowledgeSimilar Papers 제목 키워드 기반
Visual Commonsense in Pretrained Unimodal and Multimodal Models
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 thi…
AttributeVisual Commonsense TestsWorld KnowledgeWhat do Models Learn From Training on More Than Text? Measuring Visual Commonsense Knowledge
There are limitations in learning language from text alone. Therefore, recent focus has been on developing multimodal models. However, few benchmarks exist that can measure what language models learn about language from …
What do models learn from training on more than text? Measuring visual commonsense knowledge
There are limitations in learning language from text alone. Therefore, recent focus has been on developing multimodal models. However, few benchmarks exist that can measure what language models learn about language from …
Multimodal Adaptive Distillation for Leveraging Unimodal Encoders for Vision-Language Tasks
Cross-modal encoders for vision-language (VL) tasks are often pretrained with carefully curated vision-language datasets. While these datasets reach an order of 10 million samples, the labor cost is prohibitive to scale …
Question AnsweringVisual Commonsense ReasoningVisual EntailmentVisual Question Answering+1KM-BART: Knowledge Enhanced Multimodal BART for Visual Commonsense Generation
We present Knowledge Enhanced Multimodal BART (KM-BART), which is a Transformer-based sequence-to-sequence model capable of reasoning about commonsense knowledge from multimodal inputs of images and texts. We adapt the g…
Knowledge GraphsLanguage ModelingLanguage ModellingLarge Language Model