ROME: Evaluating Pre-trained Vision-Language Models on Reasoning beyond Visual Common Sense

Kankan Zhou, Eason Lai, Wei Bin Au Yeong, Kyriakos Mouratidis, Jing Jiang

Submission Type: Regular Long Paper

Submission Track: Commonsense Reasoning

Submission Track 2: Speech and Multimodality

Keywords: commonsense reasoning, multimodality, pre-trained vision-language models

Abstract: Humans possess a strong capability for reasoning beyond common sense. For example, given an unconventional image of a goldfish laying on the table next to an empty fishbowl, a human would effortlessly determine that the fish is not inside the fishbowl. The case, however, may be different for a vision-language model, whose reasoning could gravitate towards the common scenario that the fish is inside the bowl, despite the visual input. In this paper, we introduce a novel probing dataset named ROME (reasoning beyond commonsense knowledge) to evaluate whether the state-of-the-art pre-trained vision-language models have the reasoning capability to correctly interpret counter-intuitive content. ROME contains images that defy commonsense knowledge with regards to color, shape, material, size and positional relation. Experiments on the state-of-the-art pre-trained vision-language models reveal that most of these models are still largely incapable of interpreting counter-intuitive scenarios. We hope that ROME will spur further investigations on reasoning beyond commonsense knowledge in vision-language research.

Submission Number: 2966