Recently, the anchor-free object detection model has shown great potential for accuracy and speed to exceed anchor-based object detection . The attention mechanism module module can capture contextual information well,improve detection accuracy, and use sepc network to help balance abstract and detailed information, and reduce the problem of semantic gap in the featurepyramid network . Our optimal model can get39.5% COCO AP under the background of ResNet50. Whether it is anchored-based network model YOLOv3, Faster RCNN, or anchor free network model Foveabox, FSAF, FCOS. The optimal model has a certain improvement in accuracycompared with the current popular detection models .

Author(s) : Li Wang, Wei Xiang, Ruhui Xue, Kaida Zou, Laili Zhu

Links : PDF - Abstract

Code :

https://github.com/oktantod/RoboND-DeepLearning-Project


Coursera

Keywords : detection - model - network - object - anchor -

Leave a Reply

Your email address will not be published. Required fields are marked *