{"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-uniow-efficient-universal-open-world","title":"YOLO-UniOW: Efficient Universal Open-World Object Detection","arxiv_id":"2412.20645","date":"2024-12-30","proceeding":null,"authors":["Lihao Liu","Juexiao Feng","Hui Chen","Ao Wang","Lin Song","Jungong Han","Guiguang Ding"],"abstract":"Traditional object detection models are constrained by the limitations of closed-set datasets, detecting only categories encountered during training. While multimodal models have extended category recognition by aligning text and image modalities, they introduce significant inference overhead due to cross-modality fusion and still remain restricted by predefined vocabulary, leaving them ineffective at handling unknown objects in open-world scenarios. In this work, we introduce Universal Open-World Object Detection (Uni-OWD), a new paradigm that unifies open-vocabulary and open-world object detection tasks. To address the challenges of this setting, we propose YOLO-UniOW, a novel model that advances the boundaries of efficiency, versatility, and performance. YOLO-UniOW incorporates Adaptive Decision Learning to replace computationally expensive cross-modality fusion with lightweight alignment in the CLIP latent space, achieving efficient detection without compromising generalization. Additionally, we design a Wildcard Learning strategy that detects out-of-distribution objects as \"unknown\" while enabling dynamic vocabulary expansion without the need for incremental learning. This design empowers YOLO-UniOW to seamlessly adapt to new categories in open-world environments. Extensive experiments validate the superiority of YOLO-UniOW, achieving achieving 34.6 AP and 30.0 APr on LVIS with an inference speed of 69.6 FPS. The model also sets benchmarks on M-OWODB, S-OWODB, and nuScenes datasets, showcasing its unmatched performance in open-world object detection. Code and models are available at https://github.com/THU-MIG/YOLO-UniOW.","url_abs":"https://arxiv.org/abs/2412.20645v1","url_pdf":"https://arxiv.org/pdf/2412.20645v1.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-uniow-efficient-universal-open-world","repo_url":"https://github.com/thu-mig/yolo-uniow","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"open-world-object-detection","task_name":"Open World Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.20645","atlas_url":"https://app.syntology.ai/?focus=2412.20645","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}