Résumé
Synthesizing realistic images from text descriptions on a dataset like Microsoft Common Objects in Context (COCO), where each image can contain several objects, is a challenging task. Prior work has used text captions to generate images. However, captions might not be informative enough to capture the entire image and insufficient for the model to be able to understand which objects in the images correspond to which words in the captions. We show that adding a dialogue that further describes the scene leads to significant improvement in the inception score and in the quality of generated images on the COCO dataset.
| Langue originale | Anglais |
|---|---|
| État | Publié - 2018 |
| Modification externe | Oui |
| Evénement | 6th International Conference on Learning Representations, ICLR 2018 - Vancouver, Canada Durée: 30 avr. 2018 → 3 mai 2018 |
Conférence
| Conférence | 6th International Conference on Learning Representations, ICLR 2018 |
|---|---|
| Pays/Territoire | Canada |
| La ville | Vancouver |
| Période | 30/04/18 → 3/05/18 |
Classification disciplinaire ASJC Scopus
- Education
- Applications de l'informatique
- Linguistique et langues
- Langues et linguistique
Empreinte digitale
Voici les principaux termes ou expressions associés à « ChatPainter: Improving text to image generation using dialogue ». Ces libellés thématiques sont générés à partir du titre et du résumé de la publication. Ensemble, ils forment une empreinte digitale unique.Citer cette ressource
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver