Enhancing Object Detection With Fourier Series
发布时间：2025-04-01
点击次数：
- DOI码：
- 10.1109/tpami.2025.3526990
- 所属单位：
- Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & Re, Wuhan 430079, Peoples R China
- 发表刊物：
- IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
- 项目来源：
- This work was supported in part by the National Key Research and Development Program of China under
- 关键字：
- Fourier series,Object detection,Shape,Mathematical models,Transformers,Optimization,Vectors,Predictive models,Image segmentation,Gaussian distribution,closed curve of arbitrary shape,and directional vector
- 摘要：
- Traditional object detection models often lose the detailed outline information of the object. To address this problem, we propose the Fourier Series Object Detection (FSD). It encodes the object's outline closed curve into two one-dimensional periodic Fourier series. The Fourier Series Model (FSM) is constructed to regress the Fourier series for each object in the image. Thus, during inference, the detailed outline information of each object can be retrieved. We introduce Rolling Optimization Matching for Fourier loss to ensure that the model's learning process is not affected by the sequence
- 合写作者：
- Cen, Yaorong,Hu, Hui,Hong, Yong,Jiang, Ming
- 第一作者：
- Liu, Jin
- 论文类型：
- 期刊论文
- 通讯作者：
- Lu, Zhongyuan,Shao, Zhenfeng,Xu, Miaozhong
- 文献类型：
- Article
- 卷号：
- 47
- 期号：
- 4
- 页面范围：
- 2581-2596
- ISSN号：
- 0162-8828
- 是否译文：
- 否
- 发表时间：
- 2025-04-01