Compositional Generalization in Image Captioning
Mitja Nikolaus, Mostafa Abdou, Matthew Lamm, Rahul Aralikatte, Desmond Elliott
Abstract
Image captioning models are usually evaluated on their ability to describe a held-out set of images, not on their ability to generalize to unseen concepts. We study the problem of compositional generalization, which measures how well a model composes unseen combinations of concepts when describing images. State-of-the-art image captioning models show poor generalization performance on this task. We propose a multi-task model to address the poor performance, that combines caption generation and image–sentence ranking, and uses a decoding mechanism that re-ranks the captions according their similarity to the image. This model is substantially better at generalizing to unseen combinations of concepts compared to state-of-the-art captioning models.- Anthology ID:
- K19-1009
- Volume:
- Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)
- Month:
- November
- Year:
- 2019
- Address:
- Hong Kong, China
- Editors:
- Mohit Bansal, Aline Villavicencio
- Venue:
- CoNLL
- SIG:
- SIGNLL
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 87–98
- Language:
- URL:
- https://aclanthology.org/K19-1009
- DOI:
- 10.18653/v1/K19-1009
- Cite (ACL):
- Mitja Nikolaus, Mostafa Abdou, Matthew Lamm, Rahul Aralikatte, and Desmond Elliott. 2019. Compositional Generalization in Image Captioning. In Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), pages 87–98, Hong Kong, China. Association for Computational Linguistics.
- Cite (Informal):
- Compositional Generalization in Image Captioning (Nikolaus et al., CoNLL 2019)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/K19-1009.pdf
- Code
- mitjanikolaus/compositional-image-captioning
- Data
- MS COCO