Knowledge Commons of Institute of Automation,CAS
Improved Single Shot Object Detector Using Enhanced Features and Predicting Heads | |
Zhao X(赵旭)1,2![]() ![]() ![]() ![]() ![]() | |
2018-09 | |
会议名称 | 2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM) |
会议日期 | 2018-09-13~16 |
会议地点 | 中国,西安 |
摘要 | Object detection attracts much attention for its great value in theories and applications. The one-stage single shot object detectors outperform the two-stage methods in running speed with a comparable performance. In this paper, we propose three novel strategies, to further improve the performances of single shot detector without sacrificing their runtime efficiency. Firstly, we design the multi-scale context aggregation module to embeds the context information into the learned features. Secondly, we design the multi-path predicting head, which decouples the network layers and can easily learn the effective receptive fields of different aspect ratios, to detect objects of various aspect ratios better. Thirdly, we adopt a top-down feature map pyramid to detect objects using features of different semantic powers and resolutions. Sufficient ablation experiments are conducted to prove the efficiency of the proposed methods. We design a one-stage single detector named as ISSD, using the three strategies. Experimental results on PASCAL VOC 2007 and 2012 shows ISSD achieves the new state-of-the-art on accuracy with the comparable running speed. |
关键词 | 目标检测 |
学科门类 | 工学::计算机科学与技术(可授工学、理学学位) |
DOI | 10.1109/BigMM.2018.8499089 |
URL | 查看原文 |
收录类别 | EI |
语种 | 英语 |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/23596 |
专题 | 紫东太初大模型研究中心_图像与视频分析 |
通讯作者 | Tang M(唐明) |
作者单位 | 1.中国科学院自动化研究所 2.中国科学院大学 |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Zhao X,Zhao CY,Zhu YS,et al. Improved Single Shot Object Detector Using Enhanced Features and Predicting Heads[C],2018. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
AS687362573074433154(1007KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论