{"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/detclipv2-scalable-open-vocabulary-object","title":"DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment","arxiv_id":"2304.04514","date":"2023-04-10","proceeding":"CVPR 2023 1","authors":["Lewei Yao","Jianhua Han","Xiaodan Liang","Dan Xu","Wei zhang","Zhenguo Li","Hang Xu"],"abstract":"This paper presents DetCLIPv2, an efficient and scalable training framework that incorporates large-scale image-text pairs to achieve open-vocabulary object detection (OVD). Unlike previous OVD frameworks that typically rely on a pre-trained vision-language model (e.g., CLIP) or exploit image-text pairs via a pseudo labeling process, DetCLIPv2 directly learns the fine-grained word-region alignment from massive image-text pairs in an end-to-end manner. To accomplish this, we employ a maximum word-region similarity between region proposals and textual words to guide the contrastive objective. To enable the model to gain localization capability while learning broad concepts, DetCLIPv2 is trained with a hybrid supervision from detection, grounding and image-text pair data under a unified data formulation. By jointly training with an alternating scheme and adopting low-resolution input for image-text pairs, DetCLIPv2 exploits image-text pair data efficiently and effectively: DetCLIPv2 utilizes 13X more image-text pairs than DetCLIP with a similar training time and improves performance. With 13M image-text pairs for pre-training, DetCLIPv2 demonstrates superior open-vocabulary detection performance, e.g., DetCLIPv2 with Swin-T backbone achieves 40.4% zero-shot AP on the LVIS benchmark, which outperforms previous works GLIP/GLIPv2/DetCLIP by 14.4/11.4/4.5% AP, respectively, and even beats its fully-supervised counterpart by a large margin.","url_abs":"https://arxiv.org/abs/2304.04514v1","url_pdf":"https://arxiv.org/pdf/2304.04514v1.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":[],"tasks":[{"task_slug":"language-modelling","task_name":"Language Modelling"},{"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":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"low-resolution-input","method_name":"Low-resolution input"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-detection-on-odinw-full-shot-13-tasks","task":"Object Detection","dataset":"ODinW Full-Shot 13 Tasks","model":"DetCLIPv2","rank_in_archive_order":6,"of":8,"metrics":{"AP":"70.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2304.04514","atlas_url":"https://app.syntology.ai/?focus=2304.04514","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}