Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs

Roei Herzig, Alon Mendelson, Leonid Karlinsky, Assaf Arbelle, Rogerio Feris, Trevor Darrell, Amir Globerson


Abstract
Vision and language models (VLMs) have demonstrated remarkable zero-shot (ZS) performance in a variety of tasks. However, recent works have shown that even the best VLMs struggle to capture aspects of compositional scene understanding, such as object attributes, relations, and action states. In contrast, obtaining structured annotations, such as scene graphs (SGs), that could improve these models is time-consuming and costly, and thus cannot be used on a large scale. Here we ask whether small SG datasets can provide sufficient information for enhancing structured understanding of pretrained VLMs. We show that it is indeed possible to improve VLMs when learning from SGs by integrating components that incorporate structured information into both visual and textual representations. For the visual side, we incorporate a special “SG Component” in the image transformer trained to predict SG information, while for the textual side, we utilize SGs to generate fine-grained captions that highlight different compositional aspects of the scene. Our method improves the performance of several popular VLMs on multiple VL datasets with only a mild degradation in ZS capabilities.
Anthology ID:
2023.emnlp-main.870
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
14077–14098
Language:
URL:
https://aclanthology.org/2023.emnlp-main.870
DOI:
10.18653/v1/2023.emnlp-main.870
Bibkey:
Cite (ACL):
Roei Herzig, Alon Mendelson, Leonid Karlinsky, Assaf Arbelle, Rogerio Feris, Trevor Darrell, and Amir Globerson. 2023. Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 14077–14098, Singapore. Association for Computational Linguistics.
Cite (Informal):
Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs (Herzig et al., EMNLP 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/improve-issue-templates/2023.emnlp-main.870.pdf
Video:
 https://preview.aclanthology.org/improve-issue-templates/2023.emnlp-main.870.mp4