Probing Commonsense Reasoning Capability of Text-to-Image Generative Models via Non-visual Description

Autor:	Pan, Mianzhi, Li, Jianfei, Yu, Mingyue, Ma, Zheng, Cheng, Kanzhi, Zhang, Jianbing, Chen, Jiajun
Rok vydání:	2023
Předmět:	Computer Science - Multimedia
Druh dokumentu:	Working Paper
Popis:	Commonsense reasoning, the ability to make logical assumptions about daily scenes, is one core intelligence of human beings. In this work, we present a novel task and dataset for evaluating the ability of text-to-image generative models to conduct commonsense reasoning, which we call PAINTaboo. Given a description with few visual clues of one object, the goal is to generate images illustrating the object correctly. The dataset was carefully hand-curated and covered diverse object categories to analyze model performance comprehensively. Our investigation of several prevalent text-to-image generative models reveals that these models are not proficient in commonsense reasoning, as anticipated. We trust that PAINTaboo can improve our understanding of the reasoning abilities of text-to-image generative models. Comment: It is an incomplete work
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2312.07294 Zobrazit plný text záznamu View this record from Arxiv