By Jisoo Jeong, Hyojin Park, Nojun Kwak
The conventional SSD has a couple of points to be supplemented
- Each layer in the feature pyramid is used independently (the same object can be detected in multiple scales)
- Small objects are not detected well (this is not the problem only for SSD)
- The classifier network is implemented considering the relationship between layers in the feature pyramid
- The number of channels in a layer is increased efficiently
- The proposed network is suitable for sharing weights in the classifer network for different scales, resulting in a single classifier network
For more details, please refer to our arXiv paper
Please cite R-SSD in your publications if it helps your research
@article{jeong2017enhancement,
title={Enhancement of SSD by concatenating feature maps for object detection},
author={Jeong, Jisoo and Park, Hyojin and Kwak, Nojun},
journal={arXiv preprint arXiv:1705.09587},
year={2017}
}
We experimented with R-SSD using the SSD framework. To use our model, complete the installation & preparation on the SSD homepage
Pascal VOC model
Models | training batch size | mAP |
---|---|---|
R-SSD300 | 32 | 78.7 (higher than paper) |
R-SSD521 | 4 | 80.8 |
R-SSD300 with one classifier(6 boxes) | 8 | 77.0 |
To test this model, check "sh" file
# check your path in shell script (.sh file)
# cd /home/soo/caffe_ssd -> cd /your/path
./R_SSD_300model_32.sh (in file folder)