{"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/yolo-world-real-time-open-vocabulary-object","title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","arxiv_id":"2401.17270","date":"2024-01-30","proceeding":"CVPR 2024 1","authors":["Tianheng Cheng","Lin Song","Yixiao Ge","Wenyu Liu","Xinggang Wang","Ying Shan"],"abstract":"The You Only Look Once (YOLO) series of detectors have established themselves as efficient and practical tools. However, their reliance on predefined and trained object categories limits their applicability in open scenarios. Addressing this limitation, we introduce YOLO-World, an innovative approach that enhances YOLO with open-vocabulary detection capabilities through vision-language modeling and pre-training on large-scale datasets. Specifically, we propose a new Re-parameterizable Vision-Language Path Aggregation Network (RepVL-PAN) and region-text contrastive loss to facilitate the interaction between visual and linguistic information. Our method excels in detecting a wide range of objects in a zero-shot manner with high efficiency. On the challenging LVIS dataset, YOLO-World achieves 35.4 AP with 52.0 FPS on V100, which outperforms many state-of-the-art methods in terms of both accuracy and speed. Furthermore, the fine-tuned YOLO-World achieves remarkable performance on several downstream tasks, including object detection and open-vocabulary instance segmentation.","url_abs":"https://arxiv.org/abs/2401.17270v3","url_pdf":"https://arxiv.org/pdf/2401.17270v3.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":"yolo-world-real-time-open-vocabulary-object","repo_url":"https://github.com/ailab-cvc/yolo-world","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"yolo-world-real-time-open-vocabulary-object","repo_url":"https://github.com/d-robotics-ai-lab/dosod","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"yolo-world-real-time-open-vocabulary-object","repo_url":"https://github.com/ibaiGorordo/ONNX-YOLO-World-Open-Vocabulary-Object-Detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"open-vocabulary-object-detection","task_name":"Open Vocabulary Object Detection"},{"task_slug":"open-vocabulary-object-detection","task_name":"Open-vocabulary object detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"zero-shot-object-detection","task_name":"Zero-Shot Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/zero-shot-object-detection-on-lvis-v1-0","task":"Zero-Shot Object Detection","dataset":"LVIS v1.0 minival","model":"YOLO-World-L","rank_in_archive_order":8,"of":11,"metrics":{"AP":"35.4"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-object-detection-on-mscoco","task":"Zero-Shot Object Detection","dataset":"MSCOCO","model":"YOLO-World-L(without COCO data)","rank_in_archive_order":6,"of":7,"metrics":{"AP":"45.1"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2401.17270","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.17270"}},"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/d-robotics-ai-lab/dosod","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ibaiGorordo/ONNX-YOLO-World-Open-Vocabulary-Object-Detection","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ailab-cvc/yolo-world","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/AILab-CVC/YOLO-World","reach":{"status":"ok","spdx":"GPL-3.0"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"ran":0,"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":"21a47905e98284b9","entry":"compute_iou","repo":"ibaiGorordo/ONNX-YOLO-World-Open-Vocabulary-Object-Detection","repo_kind":"listed","path":"yoloworld/nms.py","file_url":"https://github.com/ibaiGorordo/ONNX-YOLO-World-Open-Vocabulary-Object-Detection/blob/HEAD/yoloworld/nms.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"21a47905e98284b9"}},{"code_sha256_prefix":"ac863afc480b7414","entry":"nms","repo":"ibaiGorordo/ONNX-YOLO-World-Open-Vocabulary-Object-Detection","repo_kind":"listed","path":"yoloworld/nms.py","file_url":"https://github.com/ibaiGorordo/ONNX-YOLO-World-Open-Vocabulary-Object-Detection/blob/HEAD/yoloworld/nms.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ac863afc480b7414"}},{"code_sha256_prefix":"b3373c000fac1860","entry":"read_class_embeddings","repo":"ibaiGorordo/ONNX-YOLO-World-Open-Vocabulary-Object-Detection","repo_kind":"listed","path":"yoloworld/YOLOWorld.py","file_url":"https://github.com/ibaiGorordo/ONNX-YOLO-World-Open-Vocabulary-Object-Detection/blob/HEAD/yoloworld/YOLOWorld.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b3373c000fac1860"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}