Authors: Hongzhen Wang, Shan Huang, Mengkai Ma Affiliations: SOT_Research
Description: The model is based on two-stage RCNN. The feature extractor is FPN with resnet. We use diverse data transformation, including scale, rotate, perspective and so on.
He K, Gkioxari G, Dollár P, et al. Mask r-cnn[C]//Proceedings of the IEEE international conference on computer vision. 2017: 2961-2969.
Ren S, He K, Girshick R, et al. Faster r-cnn: Towards real-time object detection with region proposal networks[C]//Advances in neural information processing systems. 2015: 91-99.