{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/prismer-a-vision-language-model-with-an","title":"Prismer: A Vision-Language Model with Multi-Task Experts","arxiv_id":"2303.02506","date":"2023-03-04","proceeding":null,"authors":["Shikun Liu","Linxi Fan","Edward Johns","Zhiding Yu","Chaowei Xiao","Anima Anandkumar"],"abstract":"Recent vision-language models have shown impressive multi-modal generation capabilities. However, typically they require training huge models on massive datasets. As a more scalable alternative, we introduce Prismer, a data- and parameter-efficient vision-language model that leverages an ensemble of task-specific experts. Prismer only requires training of a small number of components, with the majority of network weights inherited from multiple readily-available, pre-trained experts, and kept frozen during training. By leveraging experts from a wide range of domains, we show Prismer can efficiently pool this expert knowledge and adapt it to various vision-language reasoning tasks. In our experiments, we show that Prismer achieves fine-tuned and few-shot learning performance which is competitive with current state-of-the-arts, whilst requiring up to two orders of magnitude less training data. Code is available at https://github.com/NVlabs/prismer.","url_abs":"https://arxiv.org/abs/2303.02506v3","url_pdf":"https://arxiv.org/pdf/2303.02506v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"prismer-a-vision-language-model-with-an","repo_url":"https://github.com/nvlabs/prismer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"prismer-a-vision-language-model-with-an","repo_url":"https://github.com/KastanDay/video-pretrained-transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-captioning-on-coco-captions","task":"Image Captioning","dataset":"COCO Captions","model":"Prismer","rank_in_archive_order":18,"of":41,"metrics":{"BLEU-4":"40.4","CIDER":"136.5","METEOR":"31.4","SPICE":"24.4"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-entire","task":"Image Captioning","dataset":"nocaps entire","model":"Prismer","rank_in_archive_order":5,"of":39,"metrics":{"B1":"84.87","B2":"69.99","B3":"52.48","B4":"33.66","CIDEr":"110.84","METEOR":"31.13","ROUGE-L":"60.55","SPICE":"14.91"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-val","task":"Image Captioning","dataset":"nocaps val","model":"Prismer","rank_in_archive_order":1,"of":3,"metrics":{"CIDEr":"107.9","SPICE":"14.8"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-dev","task":"Visual Question Answering (VQA)","dataset":"VQA v2 test-dev","model":"Prismer","rank_in_archive_order":16,"of":56,"metrics":{"Accuracy":"78.43"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-std","task":"Visual Question Answering (VQA)","dataset":"VQA v2 test-std","model":"Prismer","rank_in_archive_order":11,"of":38,"metrics":{"number":"61.39","other":"69.70","overall":"78.49","yes/no":"93.09"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.02506","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}