MFM Net: modify feature map for object detection

Jinhui Qin; Weiqi Jin; Su Qiu; Li Li

doi:10.1117/12.2548140

27 November 2019 MFM Net: modify feature map for object detection

Jinhui Qin, Weiqi Jin, Su Qiu, Li Li

Proceedings Volume 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence; 113211J (2019) https://doi.org/10.1117/12.2548140
Event: The Second International Conference on Image, Video Processing and Artifical Intelligence, 2019, Shanghai, China

Abstract

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.

Citation Download Citation

Jinhui Qin, Weiqi Jin, Su Qiu, and Li Li "MFM Net: modify feature map for object detection", Proc. SPIE 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence, 113211J (27 November 2019); https://doi.org/10.1117/12.2548140

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Multiphoton fluorescence microscopy

Convolution

Sensors

Neural networks

Feature extraction

Image segmentation

Lithium

Show All Keywords

Keywords/Phrases

Search In:

Publication Years