Journal of Frontiers of Computer Science and Technology ›› 2022, Vol. 16 ›› Issue (7): 1649-1660.DOI: 10.3778/j.issn.1673-9418.2109081

• Graphics and Image • Previous Articles     Next Articles

Multi-scale Selection Pyramid Networks for Small-Sample Target Detection Algorithms

PENG Hao1, LI Xiaoming1,2,+()   

  1. 1. College of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan 030024, China
    2. Key Laboratory of Computer Science, College of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan 030024, China
  • Received:2021-08-17 Revised:2021-10-21 Online:2022-07-01 Published:2021-11-03
  • Supported by:
    the National Natural Science Foundation of China(61373099)

多尺度选择金字塔网络的小样本目标检测算法

彭豪1, 李晓明1,2,+()   

  1. 1.太原科技大学 计算机科学与技术学院,太原 030024
    2.太原科技大学 计算机科学与技术学院 计算机重点实验室,太原 030024
  • 作者简介:彭豪(1995—),男,山西运城人,硕士研究生,主要研究方向为深度学习。
    PENG Hao, born in 1995, M.S. candidate. His research interest is deep learning.
    李晓明(1965—),男,山西太原人,博士,教授,主要研究方向为图像处理与分析、计算机视觉等。
    LI Xiaoming, born in 1965, Ph.D., professor. His research interests include image processing and analysis, computer vision, etc.
  • 基金资助:
    国家自然科学基金(61373099)

Abstract:

Target detection is to detect the specified target in the image. This technology has been widely used in automatic driving, face recognition and other fields, and has become a major research hotspot in the field of computer vision at home and abroad. Traditional target detection often requires a large number of annotated datasets, so it is a challenge to detect targets with only a small number of annotated samples. To address this problem, this paper proposes a multi-scale selection pyramid network algorithm for small sample target detection so that detection no longer relies on large-scale labeled datasets. Firstly, this paper designs a multi-scale selection pyramid network for small sample target detection, which consists of three components: context layer attention module, feature scale enhancement module, and feature scale selection module. Secondly, this paper performs feature fusion after the RoI features generated by the RPN network using maximum pooling and average pooling to improve the correlation between features. This paper uses feature subtraction to highlight the category information in the features, which can improve the sensitivity to new class parameters while maintaining the stability of the model to the sample parameters. Finally, the orthogonal mapping loss function is used to constrain the features before the classification layer, which can well measure the similarity between features even in the case of a small number of samples.

Key words: target detection, small sample, orthogonal mapping loss, feature fusion

摘要:

目标检测是把图像中指定的目标检测出来,这一技术已经广泛运用于自动驾驶、人脸识别等领域,已成为国内外计算机视觉领域的一大研究热点。传统的目标检测往往需要大量标注的数据集,如何在只有少量带注释样本的情况下进行目标检测是一个挑战。针对此问题,提出了一种多尺度选择金字塔网络的小样本目标检测算法,使检测不再依赖于大规模标签数据集。首先,设计了一个用于小样本目标检测的多尺度选择金字塔网络,它由三个组件组成:上下文层注意力模块、特征尺度增强模块、特征尺度选择模块。然后,在RPN网络产生的RoI特征后采用最大池化和平均池化来提升特征之间的相关性,之后进行特征融合,并且采用特征减法来突出特征中的类别信息,在保持模型对样本参数稳定性的前提下提高了对新类参数的敏感度;最后,采用正交映射损失函数使模型在分类层前就约束特征,即使在少量样本情况下也能够很好地衡量特征间的相似性。

关键词: 目标检测, 小样本, 正交映射损失, 特征融合

CLC Number: