Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.21018 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911024027795456 |
|---|---|
| author | Hao, Lei Xu, Lina Liu, Chang Dong, Yanni |
| author_facet | Hao, Lei Xu, Lina Liu, Chang Dong, Yanni |
| contents | Effective deep feature extraction via feature-level fusion is crucial for multimodal object detection. However, previous studies often involve complex training processes that integrate modality-specific features by stacking multiple feature-level fusion units, leading to significant computational overhead. To address this issue, we propose a new fusion detection baseline that uses a single feature-level fusion unit to enable high-performance detection, thereby simplifying the training process. Based on this approach, we propose a lightweight attention-guided self-modulation feature fusion network (LASFNet), which introduces a novel attention-guided self-modulation feature fusion (ASFF) module that adaptively adjusts the responses of fusion features at both global and local levels based on attention information from different modalities, thereby promoting comprehensive and enriched feature generation. Additionally, a lightweight feature attention transformation module (FATM) is designed at the neck of LASFNet to enhance the focus on fused features and minimize information loss. Extensive experiments on three representative datasets demonstrate that, compared to state-of-the-art methods, our approach achieves a favorable efficiency-accuracy trade-off, reducing the number of parameters and computational cost by as much as 90% and 85%, respectively, while improving detection accuracy (mAP) by 1%-3%. The code will be open-sourced at https://github.com/leileilei2000/LASFNet. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_21018 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LASFNet: A Lightweight Attention-Guided Self-Modulation Feature Fusion Network for Multimodal Object Detection Hao, Lei Xu, Lina Liu, Chang Dong, Yanni Computer Vision and Pattern Recognition Effective deep feature extraction via feature-level fusion is crucial for multimodal object detection. However, previous studies often involve complex training processes that integrate modality-specific features by stacking multiple feature-level fusion units, leading to significant computational overhead. To address this issue, we propose a new fusion detection baseline that uses a single feature-level fusion unit to enable high-performance detection, thereby simplifying the training process. Based on this approach, we propose a lightweight attention-guided self-modulation feature fusion network (LASFNet), which introduces a novel attention-guided self-modulation feature fusion (ASFF) module that adaptively adjusts the responses of fusion features at both global and local levels based on attention information from different modalities, thereby promoting comprehensive and enriched feature generation. Additionally, a lightweight feature attention transformation module (FATM) is designed at the neck of LASFNet to enhance the focus on fused features and minimize information loss. Extensive experiments on three representative datasets demonstrate that, compared to state-of-the-art methods, our approach achieves a favorable efficiency-accuracy trade-off, reducing the number of parameters and computational cost by as much as 90% and 85%, respectively, while improving detection accuracy (mAP) by 1%-3%. The code will be open-sourced at https://github.com/leileilei2000/LASFNet. |
| title | LASFNet: A Lightweight Attention-Guided Self-Modulation Feature Fusion Network for Multimodal Object Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.21018 |