Declaration-based prompt tuning for visual question answering

• Main Authors: LIU, Yuhang, WEI, Wei, ZHU, Feida
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2022
• Subjects: 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; Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/sis_research/7752; https://ink.library.smu.edu.sg/context/sis_research/article/8755/viewcontent/declaration.pdf
• Institution: Singapore Management University

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.