{"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/unifying-architectures-tasks-and-modalities","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","arxiv_id":"2202.03052","date":"2022-02-07","proceeding":null,"authors":["Peng Wang","An Yang","Rui Men","Junyang Lin","Shuai Bai","Zhikang Li","Jianxin Ma","Chang Zhou","Jingren Zhou","Hongxia Yang"],"abstract":"In this work, we pursue a unified paradigm for multimodal pretraining to break the scaffolds of complex task/modality-specific customization. We propose OFA, a Task-Agnostic and Modality-Agnostic framework that supports Task Comprehensiveness. OFA unifies a diverse set of cross-modal and unimodal tasks, including image generation, visual grounding, image captioning, image classification, language modeling, etc., in a simple sequence-to-sequence learning framework. OFA follows the instruction-based learning in both pretraining and finetuning stages, requiring no extra task-specific layers for downstream tasks. In comparison with the recent state-of-the-art vision & language models that rely on extremely large cross-modal datasets, OFA is pretrained on only 20M publicly available image-text pairs. Despite its simplicity and relatively small-scale training data, OFA achieves new SOTAs in a series of cross-modal tasks while attaining highly competitive performances on uni-modal tasks. Our further analysis indicates that OFA can also effectively transfer to unseen tasks and unseen domains. Our code and models are publicly available at https://github.com/OFA-Sys/OFA.","url_abs":"https://arxiv.org/abs/2202.03052v2","url_pdf":"https://arxiv.org/pdf/2202.03052v2.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":"unifying-architectures-tasks-and-modalities","repo_url":"https://github.com/ofa-sys/ofa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"unifying-architectures-tasks-and-modalities","repo_url":"https://github.com/JHKim-snu/GVCCI","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"unifying-architectures-tasks-and-modalities","repo_url":"https://github.com/JHKim-snu/PGA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"unifying-architectures-tasks-and-modalities","repo_url":"https://github.com/modelscope/modelscope","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"object-categorization","task_name":"Object Categorization"},{"task_slug":"referring-expression","task_name":"Referring Expression"},{"task_slug":"referring-expression-comprehension","task_name":"Referring Expression Comprehension"},{"task_slug":"self-supervised-image-classification","task_name":"Self-Supervised Image Classification"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"text-summarization","task_name":"Text Summarization"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"},{"task_slug":"visual-entailment","task_name":"Visual Entailment"},{"task_slug":"visual-grounding","task_name":"Visual Grounding"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"colorjitter","method_name":"ColorJitter"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"infonce","method_name":"InfoNCE"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"moco","method_name":"MoCo"},{"method_slug":"moco-v3","method_name":"MoCo v3"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"nt-xent","method_name":"NT-Xent"},{"method_slug":"ofa","method_name":"OFA"},{"method_slug":"random-gaussian-blur","method_name":"Random Gaussian Blur"},{"method_slug":"random-resized-crop","method_name":"Random Resized Crop"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"simclr","method_name":"SimCLR"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[{"slug":"ofa","name":"OFA","full_name":"OFA"}],"results":[{"leaderboard":"/sota/image-captioning-on-coco-captions","task":"Image Captioning","dataset":"COCO Captions","model":"OFA","rank_in_archive_order":2,"of":41,"metrics":{"BLEU-4":"44.9","CIDER":"154.9","METEOR":"32.5","SPICE":"26.6"},"uses_additional_data":false},{"leaderboard":"/sota/object-categorization-on-grit","task":"Object Categorization","dataset":"GRIT","model":"OFA_Large","rank_in_archive_order":4,"of":4,"metrics":{"Categorization (ablation)":"22.6"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-image-classification-on-1","task":"Self-Supervised Image Classification","dataset":"ImageNet (finetuned)","model":"OFA (Large)","rank_in_archive_order":22,"of":65,"metrics":{"Number of Params":"473M","Top 1 Accuracy":"85.6%"},"uses_additional_data":false},{"leaderboard":"/sota/text-summarization-on-gigaword","task":"Text Summarization","dataset":"GigaWord","model":"OFA","rank_in_archive_order":6,"of":41,"metrics":{"ROUGE-1":"39.81","ROUGE-2":"20.66","ROUGE-L":"37.11"},"uses_additional_data":false},{"leaderboard":"/sota/visual-entailment-on-snli-ve-test","task":"Visual Entailment","dataset":"SNLI-VE test","model":"OFA","rank_in_archive_order":1,"of":8,"metrics":{"Accuracy":"91.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-entailment-on-snli-ve-val","task":"Visual Entailment","dataset":"SNLI-VE val","model":"OFA","rank_in_archive_order":1,"of":9,"metrics":{"Accuracy":"91.0"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-grit-1","task":"Visual Question Answering","dataset":"GRIT","model":"OFA","rank_in_archive_order":1,"of":1,"metrics":{"VQA (ablation)":"72.4"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-dev-1","task":"Visual Question Answering","dataset":"VQA v2 test-dev","model":"OFA","rank_in_archive_order":3,"of":11,"metrics":{"Accuracy":"82.0"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-std-1","task":"Visual Question Answering","dataset":"VQA v2 test-std","model":"OFA","rank_in_archive_order":2,"of":3,"metrics":{"number":"71.44","other":"73.35","overall":"81.98","yes/no":"94.66"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2202.03052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.03052"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JHKim-snu/GVCCI","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/modelscope/modelscope","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ofa-sys/ofa","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JHKim-snu/PGA","reach":{"status":"ok"}}],"summary":{"ran_honours":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"357d3a4f0be679d9","entry":"apply_half","repo":"ofa-sys/ofa","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/ofa-sys/ofa/blob/HEAD/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"357d3a4f0be679d9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}