Measuring Progress in Fine-grained Vision-and-Language Understanding

Emanuele Bugliarello, Laurent Sartran, Aishwarya Agrawal, Lisa Anne Hendricks, Aida Nematzadeh


Abstract
While pretraining on large-scale image–text data from the Web has facilitated rapid progress on many vision-and-language (V&L) tasks, recent work has demonstrated that pretrained models lack “fine-grained” understanding, such as the ability to recognise relationships, verbs, and numbers in images. This has resulted in an increased interest in the community to either develop new benchmarks or models for such capabilities. To better understand and quantify progress in this direction, we investigate four competitive V&L models on four fine-grained benchmarks. Through our analysis, we find that X-VLM (Zeng et al., 2022) consistently outperforms other baselines, and that modelling innovations can impact performance more than scaling Web data, which even degrades performance sometimes. Through a deeper investigation of X-VLM, we highlight the importance of both novel losses and rich data sources for learning fine-grained skills. Finally, we inspect training dynamics, and discover that for some tasks, performance peaks early in training or significantly fluctuates, never converging.
Anthology ID:
2023.acl-long.87
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1559–1582
Language:
URL:
https://aclanthology.org/2023.acl-long.87
DOI:
10.18653/v1/2023.acl-long.87
Bibkey:
Cite (ACL):
Emanuele Bugliarello, Laurent Sartran, Aishwarya Agrawal, Lisa Anne Hendricks, and Aida Nematzadeh. 2023. Measuring Progress in Fine-grained Vision-and-Language Understanding. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1559–1582, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Measuring Progress in Fine-grained Vision-and-Language Understanding (Bugliarello et al., ACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/2023.acl-long.87.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-2/2023.acl-long.87.mp4