{"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/clip-vg-self-paced-curriculum-adapting-of","title":"CLIP-VG: Self-paced Curriculum Adapting of CLIP for Visual Grounding","arxiv_id":"2305.08685","date":"2023-05-15","proceeding":null,"authors":["Linhui Xiao","Xiaoshan Yang","Fang Peng","Ming Yan","YaoWei Wang","Changsheng Xu"],"abstract":"Visual Grounding (VG) is a crucial topic in the field of vision and language, which involves locating a specific region described by expressions within an image. To reduce the reliance on manually labeled data, unsupervised visual grounding have been developed to locate regions using pseudo-labels. However, the performance of existing unsupervised methods is highly dependent on the quality of pseudo-labels and these methods always encounter issues with limited diversity. In order to utilize vision and language pre-trained models to address the grounding problem, and reasonably take advantage of pseudo-labels, we propose CLIP-VG, a novel method that can conduct self-paced curriculum adapting of CLIP with pseudo-language labels. We propose a simple yet efficient end-to-end network architecture to realize the transfer of CLIP to the visual grounding. Based on the CLIP-based architecture, we further propose single-source and multi-source curriculum adapting algorithms, which can progressively find more reliable pseudo-labels to learn an optimal model, thereby achieving a balance between reliability and diversity for the pseudo-language labels. Our method outperforms the current state-of-the-art unsupervised method by a significant margin on RefCOCO/+/g datasets in both single-source and multi-source scenarios, with improvements ranging from 6.78$\\%$ to 10.67$\\%$ and 11.39$\\%$ to 14.87$\\%$, respectively. The results even outperform existing weakly supervised visual grounding methods. Furthermore, our method is also competitive in fully supervised setting. The code and models are available at https://github.com/linhuixiao/CLIP-VG.","url_abs":"https://arxiv.org/abs/2305.08685v5","url_pdf":"https://arxiv.org/pdf/2305.08685v5.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":"clip-vg-self-paced-curriculum-adapting-of","repo_url":"https://github.com/linhuixiao/clip-vg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"clip-vg-self-paced-curriculum-adapting-of","repo_url":"https://github.com/linhuixiao/hivg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"clip-vg-self-paced-curriculum-adapting-of","repo_url":"https://github.com/linhuixiao/oneref","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"visual-grounding","task_name":"Visual Grounding"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2305.08685","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}