Abstract

Two optimization methods are proposed to improve faster region-based convolutional neural network (Faster R-CNN), which are (1) restructuring Faster R-CNN's backbone network and the classification and regression (C&R) network using residual networks and (2) designing the feature ensemble structure for Faster R-CNN to combine the shallow with deep feature maps of the backbone. In addition, this paper proposed a method to evaluate the model's performance, which is pixel mean value ( Pmean) distribution of different channel feature maps, and quantitatively evaluate the feature representation capability of the model. Experimental results show that mean average precision (mAP) of the model optimized by the first method can reach 86.5%, which is 1.9% higher than that of baseline. However, mAP of the model optimized by the second method reaches 87.5%, which is 2.9% higher than the baseline model. The Pmean statistics of each channel feature map extracted by different backbones show that the model accuracy is higher when the Pmean of its channel feature maps is bigger, which can effectively improve the interpretability of the model accuracy.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call