cs.CVOct 27, 2026

Dynamic Merging Mutually-Distilled Multi-View Networks for RGB-Event-based Representation Learning

Authors: Futian Wang, Fan Zhang, Xiao Wang, Yuhe Ding, Shiao Wang, Jingxi Huang, Jin Tang

Organizations: School of Computer Science and Technology, Anhui University, Hefei 230601, China · Hefei University, Hefei 230601, China

Abstract

Multi-modal fusion algorithms combining conventional frame-based cameras and event cameras have recently attracted substantial research attention. Typically, existing approaches convert event streams into frames, voxels, or tensors, and then learn the required spatiotemporal information from these transformed event representations for fusion with conventional frame-camera data. Obviously, such paradigms only exploit the limited representational capacity of event data. Moreover, standard training pipelines fail to fully leverage diverse model parameters obtained throughout the learning process. In this paper, we propose a novel mutual distillation method leveraging multi-view teacher network weights to better integrate multiple event representations and achieve model-parameter level fusion. Specifically, we employ multiple encoders to extract different types of event representations and perform mutual knowledge distillation at both the feature-level and logit-level in this process. Afterwards, we perform a dynamic hierarchical model merge strategy on the model parameters from the first stage to yield a unified multi-modal RGB-Event representation model. Experimental results across multiple event-based datasets demonstrate that our proposed framework achieves significant performance improvements.

Figures & tables

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. CMTFormer: Marrying Transformer with Hierarchical Information Interaction for RGB-Event Object Detection

    Jun 28, 2026Yu Li, Yuenan Hou, Yingmei Wei +2Event-Based VisionEvent-Based Object Detection

  2. REALM: An RGB- and Event-Aligned Latent Manifold for Cross-Modal Perception

    Apr 30, 2026Vincenzo Polizzi, David B. Lindell, Jonathan KellyMultimodal Foundation ModelsEvent-Based Vision

  3. Weaving Light and Time: Unified Harmonic-Geometric Representation Learning for Dense RGB-Event Parsing

    Jul 10, 2026Chenxu Peng, Chongtian zhou, Dicheng Liu +5Event-Based VisionVisual Representation Learning