{"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/realsyn-an-effective-and-scalable-multimodal","title":"RealSyn: An Effective and Scalable Multimodal Interleaved Document Transformation Paradigm","arxiv_id":"2502.12513","date":"2025-02-18","proceeding":null,"authors":["Tiancheng Gu","Kaicheng Yang","Chaoyi Zhang","Yin Xie","Xiang An","Ziyong Feng","Dongnan Liu","Weidong Cai","Jiankang Deng"],"abstract":"After pre-training on extensive image-text pairs, Contrastive Language-Image Pre-training (CLIP) demonstrates promising performance on a wide variety of benchmarks. However, a substantial volume of multimodal interleaved documents remains underutilized for contrastive vision-language representation learning. To fully leverage these unpaired documents, we initially establish a Real-World Data Extraction pipeline to extract high-quality images and texts. Then we design a hierarchical retrieval method to efficiently associate each image with multiple semantically relevant realistic texts. To further enhance fine-grained visual information, we propose an image semantic augmented generation module for synthetic text production. Furthermore, we employ a semantic balance sampling strategy to improve dataset diversity, enabling better learning of long-tail concepts. Based on these innovations, we construct RealSyn, a dataset combining realistic and synthetic texts, available in three scales: 15M, 30M, and 100M. We compare our dataset with other widely used datasets of equivalent scale for CLIP training. Models pre-trained on RealSyn consistently achieve state-of-the-art performance across various downstream tasks, including linear probe, zero-shot transfer, zero-shot robustness, and zero-shot retrieval. Furthermore, extensive experiments confirm that RealSyn significantly enhances contrastive vision-language representation learning and demonstrates robust scalability. To facilitate future research, the RealSyn dataset and pretrained model weights are released at https://github.com/deepglint/RealSyn.","url_abs":"https://arxiv.org/abs/2502.12513v2","url_pdf":"https://arxiv.org/pdf/2502.12513v2.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":"realsyn-an-effective-and-scalable-multimodal","repo_url":"https://github.com/deepglint/realsyn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2502.12513","atlas_url":"https://app.syntology.ai/?focus=2502.12513","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}