This paper introduces a new real-time object detection approach named Yes-Net. It realizes the prediction of bounding boxes and class via single neural network like YOLOv2 and SSD, but owns more efficient and outstanding features. It combines local information with global information by adding the RNN architecture as a packed unit in CNN model to form the basic feature extractor. Independent anchor boxes coming from full-dimension k-means is also applied in Yes-Net, it brings better average IOU than grid anchor box. In addition, instead of NMS, Yes-Net uses RNN as a filter to get the final boxes, which is more efficient. For 416 x 416 input, Yes-Net achieves 79.2% mAP on VOC2007 test at 39 FPS on an Nvidia Titan X Pascal.
@article{arxiv.1706.09180,
title = {Yes-Net: An effective Detector Based on Global Information},
author = {Liangzhuang Ma and Xin Kan and Qianjiang Xiao and Wenlong Liu and Peiqin Sun},
journal= {arXiv preprint arXiv:1706.09180},
year = {2017}
}