...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Image and Vision Computing >Multi-level refinement enriched feature pyramid network for object detection
【24h】

Multi-level refinement enriched feature pyramid network for object detection

机译：多级细化丰富的特征金字塔网络用于对象检测

获取原文
获取原文并翻译 | 示例
   

获取外文期刊封面封底 >>

       
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Class Imbalance and scales imbalance are common in object detection. A class imbalance occurs due to insufficient inequality between the number of instances with respect to different classes, while an imbalance in scale occurs when object have different scales and a different number of examples of different scales. In order to solve the problem of scale variance (scale imbalance) and class imbalance together, we propose a simple and effective feature enhancement scheme that explicitly uses all information of a multi-level structure to generate a multilevel contextual features pyramid with multiple scales. We also introduce a cascaded refinement scheme that incorporates multi-scale contextual features into the Single Shot Detector (SSD) predictive layers to improve their distinctiveness for multi-scale detection. A stack of multi-scale contextual feature modules is used in a feature enhancement scheme to merge the multi-level and multi-scale features. Then we collect the equivalent scale features over the Multi-layer Feature Fusion (MLFF) unit to construct a feature pyramid in which each feature map is made up of layers from multiple levels. More robustness and contextual information are integrated into the pyramid through chain parallel pooling operation. To improve classification and regression, a cascaded refinement scheme is proposed that effectively captures a large amount of contextual information and refines the anchors to solve the class imbalance problem. The experiments are carried out on two benchmarks datasets: MS COCO and PASCAL VOC 07/12. Our proposed approach achieves state-of-the-art accuracy with an AP of 40.6 in the case of multi-scale inference on MS COCO Test-dev (input size 320 x 320). For 512 x 512 input on the MS COCO Test-dev, our approach leads in an absolute gain in precision of 1.8% compared to the best reported results of single-stage detector (AP: 45.7). (c) 2021 Elsevier B.V. All rights reserved.
机译：类别不平衡和尺度不平衡在对象检测中很常见。由于不同类别的情况之间的情况之间的不等式不等式而发生级别的不平衡，而当物体具有不同的尺度和不同比例的示例的不同数量的示例，则发生比例的不平衡。为了解决尺度方差（规模不平衡）和类不平衡的问题，我们提出了一种简单有效的特征增强方案，明确使用多级结构的所有信息来生成具有多个尺度的金字塔的多级上下文。我们还介绍了一种级联的细化方案，该方案将多尺度上下文特征结合到单次检测器（SSD）预测层中，以改善它们的多尺度检测的独特性。一堆多尺度上下文特征模块用于特征增强方案，以合并多级和多尺度特征。然后我们收集多层特征融合（MLFF）单元上的等效刻度特征，以构造一个特征金字塔，其中每个特征映射由来自多个级别的层组成。通过链并联池操作将更多的鲁棒性和上下文信息集成到金字塔中。为了提高分类和回归，提出了一种级联的细化方案，以有效地捕获大量的上下文信息并改进锚点以解决类别不平衡问题。实验是在两个基准数据集中进行：COCO和Pascal VOC 07/12。我们所提出的方法在MS Coco Test-Dev上的多尺寸推断的情况下，通过40.6的AP实现最先进的准确性（输入大小320 x 320）。对于MS Coco Test-Dev的512 x 512输入，与单级检测器的最佳报告结果相比，我们的方法以1.8％的精确增益为导致的1.8％（AP：45.7）。 （c）2021 elestvier b.v.保留所有权利。

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