Probing Commonsense Reasoning Capability of Text-to-Image Generative Models via Non-visual Description
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917572540104704 |
|---|---|
| author | Pan, Mianzhi Li, Jianfei Yu, Mingyue Ma, Zheng Cheng, Kanzhi Zhang, Jianbing Chen, Jiajun |
| author_facet | Pan, Mianzhi Li, Jianfei Yu, Mingyue Ma, Zheng Cheng, Kanzhi Zhang, Jianbing Chen, Jiajun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_07294 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Probing Commonsense Reasoning Capability of Text-to-Image Generative Models via Non-visual Description Pan, Mianzhi Li, Jianfei Yu, Mingyue Ma, Zheng Cheng, Kanzhi Zhang, Jianbing Chen, Jiajun Multimedia 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. |
| title | Probing Commonsense Reasoning Capability of Text-to-Image Generative Models via Non-visual Description |
| topic | Multimedia |
| url | https://arxiv.org/abs/2312.07294 |