...
首页> 外文期刊>Journal of electronic imaging >Balanced-RetinaNet: solving the imbalanced problems in object detection
【24h】

Balanced-RetinaNet: solving the imbalanced problems in object detection

机译:平衡视网膜:解决物体检测中的不平衡问题

获取原文
获取原文并翻译 | 示例
           

摘要

Compared with the improvement of model structure in the field of object detection, the imbalanced problems in the training process have received less attention, but it is also one of the main reasons affecting its performance. We mainly analyze the imbalanced problems that occur in different stages of the network training process and propose a more balanced network called Balanced-RetinaNet, which has three improvements. First, in the feature extraction stage, a multi-scale feature balanced module is proposed to settle the problem in terms of imbalanced feature distribution, that is, the high-level feature lacks spatial information and while the lowlevel feature lacks semantic information; then, in the object regression stage, an interval-based regression loss is proposed to solve the problem of inaccurate localization caused by the different contributions of different samples to the regression loss; finally, in the object classification stage, an adaptive focal loss is proposed to solve the problem of classification errors caused by the loss of a large number of negative samples overwhelming the overall classification loss. Experiments have proved that by solving the imbalanced problems, the detection accuracy has been significantly improved on the MS COCO dataset. (c) 2021 SPIE and IS&T [DOI: 10.1117/1.JEI.30.3.033009]
机译:与对象检测领域的模型结构的改善相比,培训过程中的不平衡问题得到了不太关注,但它也是影响其性能的主要原因之一。我们主要分析了网络培训过程不同阶段发生的不平衡问题,并提出了一种称为平衡视网膜的平衡网络,具有三种改进。首先,在特征提取阶段,提出了一种多尺度特征平衡模块来解决问题,即在不平衡的特征分布方面,即高级功能缺少空间信息,而Lowlevel特征缺少语义信息;然后,在对象回归阶段,提出了一种基于间隔的回归损耗来解决由不同样本对回归损耗的不同贡献引起的不准确定位的问题;最后,在对象分类阶段,提出了一种自适应焦损,以解决由大量负样本丢失引起的分类误差的问题,这是压倒整体分类损失。实验证明,通过求解不平衡的问题,在MS Coco数据集上显着改善了检测精度。 (c)2021 SPIE和IS&T [DOI:10.1117 / 1.JEI.30.3.033009]

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号