DA-FPN: Deformable Convolution and Feature Alignment for Object Detection
This study sought to address the problem of the insufficient extraction of shallow object information and boundary information when using traditional FPN structures in current object detection algorithms, which degrades object detection accuracy. In this paper, a new FPN structure model, DA-FPN, is...
Main Authors: | Xiang Fu, Zemin Yuan, Tingjian Yu, Yun Ge |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-03-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/12/6/1354 |
Similar Items
-
SGR: An Improved Point-Based Method for Remote Sensing Object Detection via Dual-Domain Alignment Saliency-Guided RepPoints
by: Shuhua Mai, et al.
Published: (2024-01-01) -
A Refined Single-Stage Detector With Feature Enhancement and Alignment for Oriented Objects
by: Si-Bao Chen, et al.
Published: (2021-01-01) -
Online Detection of Fabric Defects Based on Improved CenterNet with Deformable Convolution
by: Jun Xiang, et al.
Published: (2022-06-01) -
Feature Enhancement and Alignment for Oriented Object Detection
by: Xu Xie, et al.
Published: (2024-01-01) -
HA-FPN: Hierarchical Attention Feature Pyramid Network for Object Detection
by: Jin Dang, et al.
Published: (2023-05-01)