arrow
返回

Coordinate-based anchor-free module for object detection

delete2021-04-22
delete10
PRE
AI
Z
Zhiyong Tang
J
Jianbing Yang
Z
Zhongcai Pei *
X
Xiao Song
DOI:10.1007/s10489-021-02373-8delete
delete原文链接
delete分享
delete收藏
摘要

摘要

En 中文
Despite the impressive performance of some recent state-of-the-art detectors, small target detection, scale variation, and label ambiguities remain challenges. To tackle these issues, we present a coordinate-based anchor-free (CBAF) module for object detection. It can be used as a branch of a single-shot detector (e.g., RetinaNet or SSD) or predict the output probabilities and coordinates directly. The main idea of the CBAF module is to predict the category and the adjustments to the box of the object by part feature and its contextual part features, which are based on feature maps divided by spatial coordinates. This is inspired by the fact that human beings can infer an entire object by observing the part of the surrounding environment. The CBAF module will encode and decode boxes in the anchor-free manner per feature map with different resolutions during training and testing. During training, we first use the proposed spatial coordinate partition layer to divide feature maps into several parts of size n x n and then propose a contextual building layer to fuse the part and its contextual parts together. We will demonstrate the CBAF module through a concrete implementation. The CBAF module improves AP scores of object detection with nearly no additional computation when working in conjunction with the anchor-based RetinaNet. Furthermore, experimental results on the MS-COCO dataset show that the mAP of the CBAF module has increased by 1.1%, compared with RetinaNet. When the CBAF module works in conjunction with the anchor-based RetinaNet, the mAP increased by 2.2%.
Keyword:
Anchor-free
Contextual part features
Object detection
Part feature
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Applied Intelligence 封面图
Applied Intelligence
IF:
3.5
论文数:
7.7K
被引数:
1.7W

机构

B
Beihang University
学者数:
5.2W
论文数: 4.1W
被引数: 37
引用论文

引用论文

Engineering Antibodies with C-Terminal Sortase-Mediated Modification for Targeted Nanomedicine
err2019-07-23
err0
PREAI
errRania A. Hashad; Jaclyn L. Lange; Natasha C. W. Tan; Karen Alt; Christoph E. Hagemeyer
err分享
err收藏
err分享
err收藏
Pedestrian Trajectory Prediction Based on Deep Convolutional LSTM Network
err2021-06-01
err95
errOAAI
errSong, Xiao; Chen, Kai; Li, Xu; Sun, Jinghan; Hou, Baocun; Cui, Yong; Zhang, Baochang; Xiong, Gang; Wang, Zilie
err分享
err收藏
0.9% saline is neither normal nor physiological
err2016-03-11
err0
errOAAI
errHeng Li; Shi-ren Sun; John Q. Yap; Jiang-hua Chen; Qi Qian
err分享
err收藏
Promoting Inclusive Growth
err
IF0
err2012-04-06
err0
errOAAI
err
err分享
err收藏
学者 查看更多内容