DCRN: Densely Connected Refinement Network for Object Detection

Abstract

Object detection has made great progress in recent years, the two-stage approach achieves high accuracy and the one-stage approach achieves high efficiency. In order to inherit the advantages of both while improving detection performance, this manuscript present a useful method, named Densely Connected Refinement Network (DCRN). It adds the dense connection based on RefineDet. Compare to the RefineDet, our approach can take full advantage of the bottom feature information. DCRN is formed by three interconnected modules, the dense anchor refinement module (DARM), the dense object detection module (DODM) and the dense transfer connection block (DTCB). First module can make better use of the features from different layers to initially adjust anchors by attaching dense connection. The latter module takes the refined anchors to further improve the regression and predict multi-class label. Due to the dense connection in DCRN, the network parameters are reduced and the computing costs of this approach is also saved. Extensive experimental results on PASCAL VOC 2007 and PASCAL VOC 2012 demonstrate that DCRN achieves higher accuracy than the one-stage method and higher efficiency than the two-stage method.

Deep Residual Network in Network

“…Generally, various techniques are used to improve the performance of CNNs in terms of precision or parameters and computational complexity such as increasing the depth [14,[16][17][18][19][20], changing the filter type [1,21,22], increasing the width [19,23], number of units of each layer and/or the number of feature maps (channels) [23,24], modification of convolution parameters [25][26][27][28][29] or pooling [30][31][32][33][34][35][36][37][38], changing the activation function [1,39,40], and reducing the number of parameters and resources [1,27,41]. In CNN, the computation in the convolutional layer is based on the simple linear filter.…”