Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

7-2022

Abstract

In recent years, the pre-training-then-fine-tuning paradigm has yielded immense success on a wide spectrum of cross-modal tasks, such as visual question answering (VQA), in which a visual-language (VL) model is first optimized via self-supervised task objectives, e.g., masked language modeling (MLM) and image-text matching (ITM), and then fine-tuned to adapt to downstream task (e.g., VQA) via a brand-new objective function, e.g., answer prediction. However, the inconsistency of the objective forms not only severely limits the generalization of pre-trained VL models to downstream tasks, but also requires a large amount of labeled data for fine-tuning. To alleviate the problem, we propose an innovative VL fine-tuning paradigm (named Declaration-based Prompt Tuning, abbreviated as DPT), which fine-tunes the model for downstream VQA using the pre-training objectives, boosting the effective adaptation of pre-trained models to the downstream task. Specifically, DPT reformulates the VQA task via (1) textual adaptation, which converts the given questions into declarative sentence form for prompt-tuning, and (2) task adaptation, which optimizes the objective function of VQA problem in the manner of pre-training phase. Experimental results on GQA dataset show that DPT outperforms the fine-tuned counterpart by a large margin regarding accuracy in both fully-supervised (2.68%) and zero-shot/fewshot (over 31%) settings. All the data and codes will be available to facilitate future research.

Keywords

Machine Learning: Multi-modal learning, Computer Vision: Transfer, low-shot, semi- and un- supervised learning, Computer Vision: Vision and language, Natural Language Processing: Question Answering

Discipline

Databases and Information Systems

Research Areas

Data Science and Engineering

Publication

Proceedings of the 2022 International Joint Conference on Artificial Intelligence, Vienna, Austria, July 23-29

First Page

3264

Last Page

3270

Identifier

10.24963/ijcai.2022/453

Publisher

International Joint Conferences on Artificial Intelligence

City or Country

California

Additional URL

https://doi.org/10.24963/ijcai.2022/453

Share

COinS