Focus Through Motion: RGB-Event Collaborative Token Sparsification for Efficient Object Detection

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yang, Nan, Wang, Yang, Liu, Zhanwen, Dai, Yuchao, Liu, Yang, Zhao, Xiangmo
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914021817450496
author Yang, Nan
Wang, Yang
Liu, Zhanwen
Dai, Yuchao
Liu, Yang
Zhao, Xiangmo
author_facet Yang, Nan
Wang, Yang
Liu, Zhanwen
Dai, Yuchao
Liu, Yang
Zhao, Xiangmo
contents Existing RGB-Event detection methods process the low-information regions of both modalities (background in images and non-event regions in event data) uniformly during feature extraction and fusion, resulting in high computational costs and suboptimal performance. To mitigate the computational redundancy during feature extraction, researchers have respectively proposed token sparsification methods for the image and event modalities. However, these methods employ a fixed number or threshold for token selection, hindering the retention of informative tokens for samples with varying complexity. To achieve a better balance between accuracy and efficiency, we propose FocusMamba, which performs adaptive collaborative sparsification of multimodal features and efficiently integrates complementary information. Specifically, an Event-Guided Multimodal Sparsification (EGMS) strategy is designed to identify and adaptively discard low-information regions within each modality by leveraging scene content changes perceived by the event camera. Based on the sparsification results, a Cross-Modality Focus Fusion (CMFF) module is proposed to effectively capture and integrate complementary features from both modalities. Experiments on the DSEC-Det and PKU-DAVIS-SOD datasets demonstrate that the proposed method achieves superior performance in both accuracy and efficiency compared to existing methods. The code will be available at https://github.com/Zizzzzzzz/FocusMamba.
format Preprint
id arxiv_https___arxiv_org_abs_2509_03872
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Focus Through Motion: RGB-Event Collaborative Token Sparsification for Efficient Object Detection
Yang, Nan
Wang, Yang
Liu, Zhanwen
Dai, Yuchao
Liu, Yang
Zhao, Xiangmo
Computer Vision and Pattern Recognition
Existing RGB-Event detection methods process the low-information regions of both modalities (background in images and non-event regions in event data) uniformly during feature extraction and fusion, resulting in high computational costs and suboptimal performance. To mitigate the computational redundancy during feature extraction, researchers have respectively proposed token sparsification methods for the image and event modalities. However, these methods employ a fixed number or threshold for token selection, hindering the retention of informative tokens for samples with varying complexity. To achieve a better balance between accuracy and efficiency, we propose FocusMamba, which performs adaptive collaborative sparsification of multimodal features and efficiently integrates complementary information. Specifically, an Event-Guided Multimodal Sparsification (EGMS) strategy is designed to identify and adaptively discard low-information regions within each modality by leveraging scene content changes perceived by the event camera. Based on the sparsification results, a Cross-Modality Focus Fusion (CMFF) module is proposed to effectively capture and integrate complementary features from both modalities. Experiments on the DSEC-Det and PKU-DAVIS-SOD datasets demonstrate that the proposed method achieves superior performance in both accuracy and efficiency compared to existing methods. The code will be available at https://github.com/Zizzzzzzz/FocusMamba.
title Focus Through Motion: RGB-Event Collaborative Token Sparsification for Efficient Object Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.03872