{"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/one-peace-exploring-one-general","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","arxiv_id":"2305.11172","date":"2023-05-18","proceeding":null,"authors":["Peng Wang","Shijie Wang","Junyang Lin","Shuai Bai","Xiaohuan Zhou","Jingren Zhou","Xinggang Wang","Chang Zhou"],"abstract":"In this work, we explore a scalable way for building a general representation model toward unlimited modalities. We release ONE-PEACE, a highly extensible model with 4B parameters that can seamlessly align and integrate representations across vision, audio, and language modalities. The architecture of ONE-PEACE comprises modality adapters, shared self-attention layers, and modality FFNs. This design allows for the easy extension of new modalities by adding adapters and FFNs, while also enabling multi-modal fusion through self-attention layers. To pretrain ONE-PEACE, we develop two modality-agnostic pretraining tasks, cross-modal aligning contrast and intra-modal denoising contrast, which align the semantic space of different modalities and capture fine-grained details within modalities concurrently. With the scaling-friendly architecture and pretraining tasks, ONE-PEACE has the potential to expand to unlimited modalities. Without using any vision or language pretrained model for initialization, ONE-PEACE achieves leading results on a wide range of uni-modal and multi-modal tasks, including image classification (ImageNet), semantic segmentation (ADE20K), audio-text retrieval (AudioCaps, Clotho), audio classification (ESC-50, FSD50K, VGGSound), audio question answering (AVQA), image-text retrieval (MSCOCO, Flickr30K), and visual grounding (RefCOCO/+/g). Code is available at https://github.com/OFA-Sys/ONE-PEACE.","url_abs":"https://arxiv.org/abs/2305.11172v1","url_pdf":"https://arxiv.org/pdf/2305.11172v1.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":"one-peace-exploring-one-general","repo_url":"https://github.com/OFA-Sys/ONE-PEACE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"one-peace-exploring-one-general","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":"1-image-2-2-stitchi","task_name":"1 Image, 2*2 Stitchi"},{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"audio-classification","task_name":"Audio Classification"},{"task_slug":"audio-question-answering","task_name":"Audio Question Answering"},{"task_slug":"audio-to-text-retrieval","task_name":"Audio to Text Retrieval"},{"task_slug":"audio-visual-question-answering-avqa","task_name":"Audio-Visual Question Answering (AVQA)"},{"task_slug":null,"task_name":"AudioCaps"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-text-retrieval","task_name":"Image-text Retrieval"},{"task_slug":"image-to-text-retrieval","task_name":"Image-to-Text Retrieval"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"referring-expression-comprehension","task_name":"Referring Expression Comprehension"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"self-supervised-image-classification","task_name":"Self-Supervised Image Classification"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"text-retrieval","task_name":"Text Retrieval"},{"task_slug":"text-to-audio-retrieval","task_name":"Text to Audio Retrieval"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"zero-shot-environment-sound-classification","task_name":"Zero-Shot Environment Sound Classification"},{"task_slug":"zero-shot-text-to-image-retrieval","task_name":"Zero-shot Text-to-Image Retrieval"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"ONE-PEACE","rank_in_archive_order":26,"of":207,"metrics":{"Acc@1":"88.1","Acc@5":"97.8"},"uses_additional_data":false},{"leaderboard":"/sota/audio-classification-on-fsd50k","task":"Audio Classification","dataset":"FSD50K","model":"ONE-PEACE","rank_in_archive_order":1,"of":10,"metrics":{"mAP":"69.7"},"uses_additional_data":true},{"leaderboard":"/sota/audio-classification-on-vggsound","task":"Audio Classification","dataset":"VGGSound","model":"ONE-PEACE (Audio-Visual)","rank_in_archive_order":3,"of":23,"metrics":{"Top 1 Accuracy":"68.2"},"uses_additional_data":true},{"leaderboard":"/sota/audio-classification-on-vggsound","task":"Audio Classification","dataset":"VGGSound","model":"ONE-PEACE (Audio-Only)","rank_in_archive_order":12,"of":23,"metrics":{"Top 1 Accuracy":"59.6"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ONE-PEACE","rank_in_archive_order":1058,"of":1060,"metrics":{"Number of params":"1520M"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-text-retrieval-on-coco","task":"Image-to-Text Retrieval","dataset":"COCO (Common Objects in Context)","model":"ONE-PEACE (ViT-G, w/o ranking)","rank_in_archive_order":2,"of":9,"metrics":{"Recall@1":"84.1","Recall@10":"98.3","Recall@5":"96.3"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-text-retrieval-on-flickr30k","task":"Image-to-Text Retrieval","dataset":"Flickr30k","model":"ONE-PEACE (finetuned, w/o ranking)","rank_in_archive_order":3,"of":11,"metrics":{"Recall@1":"97.6","Recall@10":"100","Recall@5":"100"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k","task":"Semantic Segmentation","dataset":"ADE20K","model":"ONE-PEACE","rank_in_archive_order":2,"of":235,"metrics":{"Params (M)":"1500","Validation mIoU":"63.0"},"uses_additional_data":true},{"leaderboard":"/sota/text-to-audio-retrieval-on-audiocaps","task":"Text to Audio Retrieval","dataset":"AudioCaps","model":"ONE-PEACE","rank_in_archive_order":3,"of":11,"metrics":{"R@1":"42.5","R@10":"88.4","R@5":"77.5"},"uses_additional_data":true},{"leaderboard":"/sota/text-to-audio-retrieval-on-clotho","task":"Text to Audio Retrieval","dataset":"Clotho","model":"ONE-PEACE","rank_in_archive_order":5,"of":12,"metrics":{"R@1":"22.4","R@10":"62.7","R@5":"49.0"},"uses_additional_data":true},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-dev","task":"Visual Question Answering (VQA)","dataset":"VQA v2 test-dev","model":"ONE-PEACE","rank_in_archive_order":4,"of":56,"metrics":{"Accuracy":"82.6"},"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":"ONE-PEACE","rank_in_archive_order":3,"of":38,"metrics":{"number":"72.24","other":"74.15","overall":"82.52","yes/no":"94.85"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.11172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11172"}},"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/modelscope/modelscope","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/OFA-Sys/ONE-PEACE","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":1,"ran_honours":1,"unverified":5},"by_repo_kind":{"official":{"samples":7,"ran":2,"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":"8cd8cb0d1e9e63e4","entry":"Linear","repo":"OFA-Sys/ONE-PEACE","repo_kind":"official","path":"one_peace/models/components.py","file_url":"https://github.com/OFA-Sys/ONE-PEACE/blob/HEAD/one_peace/models/components.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8cd8cb0d1e9e63e4"}},{"code_sha256_prefix":"357d3a4f0be679d9","entry":"apply_half","repo":"OFA-Sys/ONE-PEACE","repo_kind":"official","path":"one_peace/evaluate.py","file_url":"https://github.com/OFA-Sys/ONE-PEACE/blob/HEAD/one_peace/evaluate.py","link_basis":"harvester_set","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"}},{"code_sha256_prefix":"04b37e9f45497473","entry":"Embedding","repo":"OFA-Sys/ONE-PEACE","repo_kind":"official","path":"one_peace/models/components.py","file_url":"https://github.com/OFA-Sys/ONE-PEACE/blob/HEAD/one_peace/models/components.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"04b37e9f45497473"}},{"code_sha256_prefix":"1d799a47485cfcf6","entry":"LayerNorm","repo":"OFA-Sys/ONE-PEACE","repo_kind":"official","path":"one_peace/models/components.py","file_url":"https://github.com/OFA-Sys/ONE-PEACE/blob/HEAD/one_peace/models/components.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1d799a47485cfcf6"}},{"code_sha256_prefix":"a6989b09a93e6f96","entry":"adjust_label_smoothed_nll_loss","repo":"OFA-Sys/ONE-PEACE","repo_kind":"official","path":"one_peace/criterions/audio_text_pretrain_loss.py","file_url":"https://github.com/OFA-Sys/ONE-PEACE/blob/HEAD/one_peace/criterions/audio_text_pretrain_loss.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a6989b09a93e6f96"}},{"code_sha256_prefix":"144a402fb971b36a","entry":"apply_bfloat16","repo":"OFA-Sys/ONE-PEACE","repo_kind":"official","path":"one_peace/evaluate.py","file_url":"https://github.com/OFA-Sys/ONE-PEACE/blob/HEAD/one_peace/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"144a402fb971b36a"}},{"code_sha256_prefix":"0778ee3f6d86f89f","entry":"gather_without_grad","repo":"OFA-Sys/ONE-PEACE","repo_kind":"official","path":"one_peace/criterions/audio_text_pretrain_loss.py","file_url":"https://github.com/OFA-Sys/ONE-PEACE/blob/HEAD/one_peace/criterions/audio_text_pretrain_loss.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0778ee3f6d86f89f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}