{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T17:06:08Z","timestamp":1780765568146,"version":"3.54.1"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7]]},"abstract":"<jats:p>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\n\nmodels 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.<\/jats:p>","DOI":"10.24963\/ijcai.2022\/453","type":"proceedings-article","created":{"date-parts":[[2022,7,16]],"date-time":"2022-07-16T02:55:56Z","timestamp":1657940156000},"page":"3264-3270","source":"Crossref","is-referenced-by-count":14,"title":["Declaration-based Prompt Tuning for Visual Question Answering"],"prefix":"10.24963","author":[{"given":"Yuhang","family":"Liu","sequence":"first","affiliation":[{"name":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology, China"},{"name":"Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL), China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Wei","sequence":"additional","affiliation":[{"name":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology, China"},{"name":"Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL), China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daowan","family":"Peng","sequence":"additional","affiliation":[{"name":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology, China"},{"name":"Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL), China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feida","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10584","event":{"name":"Thirty-First International Joint Conference on Artificial Intelligence {IJCAI-22}","theme":"Artificial Intelligence","location":"Vienna, Austria","acronym":"IJCAI-2022","number":"31","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2022,7,23]]},"end":{"date-parts":[[2022,7,29]]}},"container-title":["Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T11:09:48Z","timestamp":1658142588000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2022\/453"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2022\/453","relation":{},"subject":[],"published":{"date-parts":[[2022,7]]}}}