MFM Net: Modify feature map for object detection

Jinhui Qin, Weiqi Jin, Su Qiu, Li Li

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Object detection, the important task in computer vision, is widely used in face recognition and unmanned drive. Based on VGG161, a fast and simple backbone comparing to deeper network, this paper proposes a new block, named Modify Feature Map (MFM) Block, to improve feature maps, leading from two facts: different channel in the feature map represents different feature in an image; every position in a feature map belong to the object or background. We establish MFM Net to predict location and classification. Some experiments on Pascal VOC 2007 and MS COCO show that MFM Net can achieve high performance with real-time speed.

源语言英语
主期刊名2019 International Conference on Image and Video Processing, and Artificial Intelligence
编辑Ruidan Su
出版商SPIE
ISBN(电子版)9781510634091
DOI
出版状态已出版 - 2019
活动2019 2nd International Conference on Image and Video Processing, and Artificial Intelligence, IVPAI 2019 - Shanghai, 中国
期限: 23 8月 201925 8月 2019

出版系列

姓名Proceedings of SPIE - The International Society for Optical Engineering
11321
ISSN(印刷版)0277-786X
ISSN(电子版)1996-756X

会议

会议2019 2nd International Conference on Image and Video Processing, and Artificial Intelligence, IVPAI 2019
国家/地区中国
Shanghai
时期23/08/1925/08/19

指纹

探究 'MFM Net: Modify feature map for object detection' 的科研主题。它们共同构成独一无二的指纹。

引用此