A path aggregation network with deformable convolution for visual object detection
Year: 2025
Type: article
Abstract: One of the main challenges encountered in visual object detection is the multi-scale issue. Many approaches have been proposed to tackle this issue. In this article, we propose a novel neck that can perform effective fusion of multi-scale features for a single-stage object detector. This neck, named the deformable convolution and path aggregation network (DePAN), is an integration of a path aggregation network with a deformable convolution block added to the feature fusion branch to improve the flexibility of feature point sampling. The deformable convolution block is implemented by repeated stacking of a deformable convolution cell. The DePAN neck can be plugged in and easily applied to various models for object detection. We apply the proposed neck to the baseline models of Yolov6-N and YOLOV6-T, and test the improved models on COCO2017 and PASCAL VOC2012 datasets, as well as a medical image dataset. The experimental results verify the effectiveness and applicability in real-world object detection.
Source: PeerJ Computer Science
Authors: Chengming Rao, Zunhao Hu, QiMing Zhao, Min Shan, Li Mao
Institutions: Jiangnan University, Wuxi Institute of Technology
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $1,395
OpenAlex ID: W4413292729