基于课程学习思想的目标检测增强算法

目标检测算法性能优劣既依赖于数据集样本分布,又依赖于特征提取网络设计.从这2点出发,首先通过分析COCO 2017数据集各尺度目标属性分布,探索了数据集固有的导致小目标检测准确率偏低的潜在因素,据此提出CP模块,该模块以离线方式调整数据集小目标分布,一方面对包含小目标图片进行上采样,另一方面对图片内小目标进行复制粘贴....

Object Detection Enhancement Algorithm Based on Curriculum Learning

The performance of object detection algorithms depends on both dataset distribution and network design of feature extraction.Starting from these two points,we firstly explore the potential inherent reasons that lead to low detection accuracy of small object by analyzing the distribution of object attributes at various scales in the COCO 2017 dataset,and propose copy and paste(CP)module accordingly,which adjusts the distribution of small object offline,on the one hand,upsampling the pictures containing small objects,on the other hand,copying and pasting the small objects in the pictures.Then,to further improve network feature extraction ability,inspired by the idea of curriculum learning(CL),we propose CL layer,which uses ground truth labels to guide the learning process,and CL factor to control the learning intensity,the features of objects are enhanced to facilitate network feature extraction.We deploy the CP module on the COCO 2017 dataset and embed the CL layer in the CenterNet network to conduct multiple sets of comparative experiments,and use average detection accuracy,small object detection accuracy,medium object detection accuracy,and large object detection accuracy as evaluation indicators.The experimental results prove the effectiveness of CP module and CL layer.