复杂端到端场景的跨视觉域目标检测算法
Cross-Domain Object Detection Algorithm for Complex End-to-End Scene Understanding
陈傲然 1黄海 1朱玥琰 1薛俊笙1
作者信息
- 1. 北京邮电大学 信息与通信工程学院,北京100876
- 折叠
摘要
深度学习应用往往假设部署场景与训练数据具有相似的视觉域特征分布,但是在复杂端到端场景中该假设并不总是成立,难以满足开放环境中智能检测业务的需求.为此,提出了基于人工智能闭环组合理论与跨视觉域的目标检测算法,在检测框架中引入多尺度卷积层构建检测算法的主干网络与瓶颈层网络,提出带有长距离依赖注意力的视觉域判别器作为二次检测头细化检测结果,设计基于空间重构注意力单元的背景聚焦模块进行伪背景图的聚焦学习,从而提升跨视觉域目标检测的准确率.实验结果表明,所提算法在跨视觉域场景中目标检测平均准确率相比双阶段算法提高6.9％,相比单阶段算法提高9.0％.
Abstract
Conventional deep learning training approaches often assume a similarity between the deployment scenario and the visual domain features present in the training data.However,this assumption might not hold true in complex end-to-end scenarios,making it difficult to meet the demands of intelligent detection services in open environments.In response,an object detection algorithm based on artificial intelligence closed-loop ensemble theory with cross-domain capabilities has been introduced.Within the detection framework,construct a backbone network and bottleneck layer network with multi-scale convolutional layers.A visual domain discriminator featuring long-range dependency attention works as a secondary detection head to refine the results.Moreover,a background focusing module,based on spatial reconstruction attention units,is able to enhance learning focused on pseudo-background representations,thereby improving the accuracy of cross-domain object detection.Experimental results show that,compared to two-stage algorithms,the proposed algorithm yields an average precision increase 6.9％,and surpasses single-stage algorithms by 9.0％ in complex end-to-end scenarios.
关键词
体系化人工智能/计算机视觉/神经网络/目标检测Key words
holistic artificial intelligence/computer vision/neural network/object detection引用本文复制引用
基金项目
国家重点研发计划项目(2021YFF0900700)
出版年
2024
NETL
NSTL
万方数据