{"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/dmr-decomposed-multi-modality-representations","title":"DMR: Decomposed Multi-Modality Representations for Frames and Events Fusion in Visual Reinforcement Learning","arxiv_id":null,"date":"2024-01-01","proceeding":"CVPR 2024 1","authors":["Haoran Xu","Peixi Peng","Guang Tan","Yuan Li","Xinhai Xu","Yonghong Tian"],"abstract":"    We explore visual reinforcement learning (RL) using two complementary visual modalities: frame-based RGB camera and event-based Dynamic Vision Sensor (DVS). Existing multi-modality visual RL methods often encounter challenges in effectively extracting task-relevant information from multiple modalities while suppressing the increased noise only using indirect reward signals instead of pixel-level supervision. To tackle this we propose a Decomposed Multi-Modality Representation (DMR) framework for visual RL. It explicitly decomposes the inputs into three distinct components: combined task-relevant features (co-features) RGB-specific noise and DVS-specific noise. The co-features represent the full information from both modalities that is relevant to the RL task; the two noise components each constrained by a data reconstruction loss to avoid information leak are contrasted with the co-features to maximize their difference. Extensive experiments demonstrate that by explicitly separating the different types of information our approach achieves substantially improved policy performance compared to state-of-the-art approaches.    ","url_abs":"http://openaccess.thecvf.com//content/CVPR2024/html/Xu_DMR_Decomposed_Multi-Modality_Representations_for_Frames_and_Events_Fusion_in_CVPR_2024_paper.html","url_pdf":"http://openaccess.thecvf.com//content/CVPR2024/papers/Xu_DMR_Decomposed_Multi-Modality_Representations_for_Frames_and_Events_Fusion_in_CVPR_2024_paper.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":"dmr-decomposed-multi-modality-representations","repo_url":"https://github.com/kyoran/dmr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}