{"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/scaling-open-vocabulary-object-detection-1","title":"Scaling Open-Vocabulary Object Detection","arxiv_id":"2306.09683","date":"2023-06-16","proceeding":"NeurIPS 2023 11","authors":["Matthias Minderer","Alexey Gritsenko","Neil Houlsby"],"abstract":"Open-vocabulary object detection has benefited greatly from pretrained vision-language models, but is still limited by the amount of available detection training data. While detection training data can be expanded by using Web image-text pairs as weak supervision, this has not been done at scales comparable to image-level pretraining. Here, we scale up detection data with self-training, which uses an existing detector to generate pseudo-box annotations on image-text pairs. Major challenges in scaling self-training are the choice of label space, pseudo-annotation filtering, and training efficiency. We present the OWLv2 model and OWL-ST self-training recipe, which address these challenges. OWLv2 surpasses the performance of previous state-of-the-art open-vocabulary detectors already at comparable training scales (~10M examples). However, with OWL-ST, we can scale to over 1B examples, yielding further large improvement: With an L/14 architecture, OWL-ST improves AP on LVIS rare classes, for which the model has seen no human box annotations, from 31.2% to 44.6% (43% relative improvement). OWL-ST unlocks Web-scale training for open-world localization, similar to what has been seen for image classification and language modelling.","url_abs":"https://arxiv.org/abs/2306.09683v3","url_pdf":"https://arxiv.org/pdf/2306.09683v3.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":"scaling-open-vocabulary-object-detection-1","repo_url":"https://github.com/google-research/scenic/tree/main/scenic/projects/owl_vit","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null},{"paper_slug":"scaling-open-vocabulary-object-detection-1","repo_url":"https://github.com/MindCode-4/code-2/tree/main/owlvit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"scaling-open-vocabulary-object-detection-1","repo_url":"https://github.com/yangyucheng000/University/tree/main/model-1/owlv2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"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":"zero-shot-object-detection","task_name":"Zero-Shot Object Detection"},{"task_slug":"image-classification","task_name":"image-classification"},{"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":"OWLv2 (OWL-ST+FT)","rank_in_archive_order":4,"of":11,"metrics":{"AP":"51.3"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-object-detection-on-lvis-v1-0-val","task":"Zero-Shot Object Detection","dataset":"LVIS v1.0 val","model":"OWLv2 (OWL-ST+FT)","rank_in_archive_order":4,"of":9,"metrics":{"AP":"47.0"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.09683","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}