Research on Target Detection Algorithm Based on Knowledge Distillation
At present,Faster Rcnn is one of the mainstream target detection frameworks.The improvement of detection accu-racy is accompanied by a deeper feature extraction network,but large number of parameters and additional computational overhead make it difficult to apply these algorithms to storage space and parameter requirements on mobile devices.In order to reduce the com-plexity of the model while maintaining performance similar to the complex network,this paper uses the knowledge distillation meth-od in the feature extraction network of the target detection framework.In order to better improve the performance of the shallow fea-ture extraction network,feature fusion technology is introduced in the knowledge distillation stage.In the case of the same network scale,the detection accuracy of the feature extraction network using this method is 6.53%higher than that of the feature extraction network without knowledge distillation.While ensuring the increase in detection speed,the accuracy of the shallow network after dis-tillation is similar to that of the complex network,which proves the effectiveness of the method in this paper.
国家科技期刊平台
NSTL
万方数据
