Retrieval-augmented Image Captioning

Rita Ramos, Desmond Elliott, Bruno Martins


Abstract
Inspired by retrieval-augmented language generation and pretrained Vision and Language (V&L) encoders, we present a new approach to image captioning that generates sentences given the input image and a set of captions retrieved from a datastore, as opposed to the image alone. The encoder in our model jointly processes the image and retrieved captions using a pretrained V&L BERT, while the decoder attends to the multimodal encoder representations, benefiting from the extra textual evidence from the retrieved captions. Experimental results on the COCO dataset show that image captioning can be effectively formulated from this new perspective. Our model, named EXTRA, benefits from using captions retrieved from the training dataset, and it can also benefit from using an external dataset without the need for retraining. Ablation studies show that retrieving a sufficient number of captions (e.g., k=5) can improve captioning quality. Our work contributes towards using pretrained V&L encoders for generative tasks, instead of standard classification tasks.
Anthology ID:
2023.eacl-main.266
Volume:
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3666–3681
Language:
URL:
https://aclanthology.org/2023.eacl-main.266
DOI:
10.18653/v1/2023.eacl-main.266
Bibkey:
Cite (ACL):
Rita Ramos, Desmond Elliott, and Bruno Martins. 2023. Retrieval-augmented Image Captioning. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 3666–3681, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Retrieval-augmented Image Captioning (Ramos et al., EACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.eacl-main.266.pdf
Video:
 https://aclanthology.org/2023.eacl-main.266.mp4