{"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/comp-continual-multimodal-pre-training-for","title":"CoMP: Continual Multimodal Pre-training for Vision Foundation Models","arxiv_id":"2503.18931","date":"2025-03-24","proceeding":null,"authors":["Yitong Chen","Lingchen Meng","Wujian Peng","Zuxuan Wu","Yu-Gang Jiang"],"abstract":"Pre-trained Vision Foundation Models (VFMs) provide strong visual representations for a wide range of applications. In this paper, we continually pre-train prevailing VFMs in a multimodal manner such that they can effortlessly process visual inputs of varying sizes and produce visual representations that are more aligned with language representations, regardless of their original pre-training process. To this end, we introduce CoMP, a carefully designed multimodal pre-training pipeline. CoMP uses a Continual Rotary Position Embedding to accommodate visual inputs with different resolutions, and an Alignment Loss between visual and textual features for better cross-modal alignment. After continual pre-training, leading VFMs like DINOv2, SigLIP and AIMv2 achieve remarkable improvements not only in multimodal understanding tasks but also in generic classification and segmentation tasks. Remarkably, CoMP-AIMv2 achieves scores of 64.9 on ChartQA with a 0.5B LLM, while maintaining an 87.3% accuracy on ImageNet-1K and a 51.8 mIoU on ADE20K under frozen chunk evaluation.","url_abs":"https://arxiv.org/abs/2503.18931v2","url_pdf":"https://arxiv.org/pdf/2503.18931v2.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":"comp-continual-multimodal-pre-training-for","repo_url":"https://github.com/SliMM-X/CoMP-MM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"cross-modal-alignment","task_name":"cross-modal alignment"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.18931","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}