Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.14726 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908597921775616 |
|---|---|
| author | Xie, Dingzhou Lan, Rushi Pang, Cheng Ning, Enhao Zeng, Jiahao Zheng, Wei |
| author_facet | Xie, Dingzhou Lan, Rushi Pang, Cheng Ning, Enhao Zeng, Jiahao Zheng, Wei |
| contents | Recent object detection methods have made remarkable progress by leveraging attention mechanisms to improve feature discriminability. However, most existing approaches are confined to refining single-layer or fusing dual-layer features, overlooking the rich inter-layer dependencies across multi-scale representations. This limits their ability to capture comprehensive contextual information essential for detecting objects with large scale variations. In this paper, we propose a novel Cross-Layer Feature Self-Attention Module (CFSAM), which holistically models both local and global dependencies within multi-scale feature maps. CFSAM consists of three key components: a convolutional local feature extractor, a Transformer-based global modeling unit that efficiently captures cross-layer interactions, and a feature fusion mechanism to restore and enhance the original representations. When integrated into the SSD300 framework, CFSAM significantly boosts detection performance, achieving 78.6% mAP on PASCAL VOC (vs. 75.5% baseline) and 52.1% mAP on COCO (vs. 43.1% baseline), outperforming existing attention modules. Moreover, the module accelerates convergence during training without introducing substantial computational overhead. Our work highlights the importance of explicit cross-layer attention modeling in advancing multi-scale object detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_14726 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Cross-Layer Feature Self-Attention Module for Multi-Scale Object Detection Xie, Dingzhou Lan, Rushi Pang, Cheng Ning, Enhao Zeng, Jiahao Zheng, Wei Computer Vision and Pattern Recognition Recent object detection methods have made remarkable progress by leveraging attention mechanisms to improve feature discriminability. However, most existing approaches are confined to refining single-layer or fusing dual-layer features, overlooking the rich inter-layer dependencies across multi-scale representations. This limits their ability to capture comprehensive contextual information essential for detecting objects with large scale variations. In this paper, we propose a novel Cross-Layer Feature Self-Attention Module (CFSAM), which holistically models both local and global dependencies within multi-scale feature maps. CFSAM consists of three key components: a convolutional local feature extractor, a Transformer-based global modeling unit that efficiently captures cross-layer interactions, and a feature fusion mechanism to restore and enhance the original representations. When integrated into the SSD300 framework, CFSAM significantly boosts detection performance, achieving 78.6% mAP on PASCAL VOC (vs. 75.5% baseline) and 52.1% mAP on COCO (vs. 43.1% baseline), outperforming existing attention modules. Moreover, the module accelerates convergence during training without introducing substantial computational overhead. Our work highlights the importance of explicit cross-layer attention modeling in advancing multi-scale object detection. |
| title | Cross-Layer Feature Self-Attention Module for Multi-Scale Object Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.14726 |