3.8 Proceedings Paper

Extend the shallow part of Single Shot MultiBox Detector via Convolutional Neural Network

Publisher

SPIE-INT SOC OPTICAL ENGINEERING
DOI: 10.1117/12.2503001

Keywords

real-time object detection; single shot multi-box detector; deep learning

Funding

  1. Natural Science Foundation of Shenzhen [JCYJ20160506172651253]
  2. National Science and Technology Support Program [2015BAK01B04]

Ask authors/readers for more resources

Single Shot MultiBox Detector (SSD) is one of the fastest algorithms in the current object detection field, which uses fully convolutional neural network to detect all scaled objects in an image. Deconvolutional Single Shot Detector (DSSD) is an approach which introduces more context information by adding the deconvolution module to SSD. And the mean Average Precision (mAP) of DSSD on PASCAL VOC2007 is improved from SSD's 77.5% to 78.6%. Although DSSD obtains higher mAP than SSD by 1.1%, the frames per second (FPS) decreases from 46 to 11.8. In this paper, we propose a single stage end-to-end image detection model called ESSD to overcome this dilemma. Our solution to this problem is to cleverly extend better context information for the shallow layers of the best single stage (e.g. SSD) detectors. Experimental results show that our model can reach 79.4% mAP, which is higher than DSSD and SSD by 0.8 and 1.9 points respectively. For 300x300 input, our testing speed is 25 FPS in single Nvidia Titan X GPU which is more than the original execution speed of DSSD.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

3.8
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available