当前位置: X-MOL 学术Cognit. Comput. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Local Enhancement and Bidirectional Feature Refinement Network for Single-Shot Detector
Cognitive Computation ( IF 5.4 ) Pub Date : 2021-02-15 , DOI: 10.1007/s12559-020-09814-5
Pengxiang Ouyang , Jiaqi Zhu , Chaogang Fan , Zhao Niu , Shu Zhan

Benefit from multi-scale feature pyramid methods, recently single-stage object detectors have achieved promising accuracy and fast inference speed. However, the majority of existing feature pyramid detection techniques only simply describe complex contextual relationships from different scales. Not only are there no effective modules that adaptively extend appropriate semantic information from deeper layers, but the finer spatial localization cues from lower layers are often ignored. In this paper, we present a Local Enhancement and Bidirectional Feature Refinement Network (LFBFR), which includes two optimization methods to achieve remarkable improvements in detection accuracy. Firstly, to make the backbone more suitable for detection task, we modify the pre-trained classification backbone to mitigate the loss of details in small objects due to consecutive decrease of the image resolution. Then we propose a Bidirectional Feature Refinement Pyramid, which can effectively utilize the inter-channel relationship of higher-level features and fine appearance cues from lower-level features by using the attention residual refinement module and the feature reuse module. Ultimately, to assess the performance of the proposed LFBFR, we design a powerful end-to-end single-stage detector called LFBFR-SSD by embedding it into the framework of SSD. Extensive experiments on the PASCAL VOC and MS COCO verify that our LFBFR-SSD outperforms a lot of state-of-the-art detectors while maintaining a real-time speed.



中文翻译:

单发检测器的局部增强和双向特征细化网络

得益于多尺度特征金字塔方法,最近的单级目标检测器已经实现了有希望的精度和快速的推理速度。然而,大多数现有的特征金字塔检测技术仅简单地描述了来自不同尺度的复杂上下文关系。不仅没有有效的模块可以自适应地从较深的层扩展适当的语义信息,而且经常会忽略较低层的较细的空间定位提示。在本文中,我们提出了一种局部增强和双向特征细化网络(LFBFR),其中包括两种优化方法,可以显着提高检测精度。首先,为了使骨干网更适合于检测任务,我们修改了预先训练的分类主干,以减轻由于图像分辨率连续降低而导致的小物体细节损失。然后,我们提出了一种双向特征细化金字塔,通过使用注意力残差细化模块和特征重用模块,可以有效地利用较高层特征的通道间关系和来自较低层特征的精细外观提示。最终,为了评估所提出的LFBFR的性能,我们将其嵌入到SSD框架中,设计了一款功能强大的端对端单级检测器LFBFR-SSD。在PASCAL VOC和MS COCO上进行的大量实验证明,我们的LFBFR-SSD在保持实时速度的同时,胜过许多最新的检测器。然后,我们提出了一种双向特征细化金字塔,通过使用注意力残差细化模块和特征重用模块,可以有效地利用较高层特征的通道间关系和来自较低层特征的精细外观提示。最终,为了评估所提出的LFBFR的性能,我们将其嵌入到SSD框架中,设计了一款功能强大的端对端单级检测器LFBFR-SSD。在PASCAL VOC和MS COCO上进行的大量实验证明,我们的LFBFR-SSD在保持实时速度的同时,胜过许多最新的检测器。然后,我们提出了一种双向特征细化金字塔,通过使用注意力残差细化模块和特征重用模块,可以有效地利用较高层特征的通道间关系和来自较低层特征的精细外观提示。最终,为了评估所提出的LFBFR的性能,我们将其嵌入到SSD框架中,设计了一款功能强大的端对端单级检测器LFBFR-SSD。在PASCAL VOC和MS COCO上进行的大量实验证明,我们的LFBFR-SSD在保持实时速度的同时,胜过许多最新的检测器。为了评估所提出的LFBFR的性能,我们将其嵌入到SSD框架中,设计了一个功能强大的端到端单级检测器LFBFR-SSD。在PASCAL VOC和MS COCO上进行的大量实验证明,我们的LFBFR-SSD在保持实时速度的同时,胜过许多最新的检测器。为了评估所提出的LFBFR的性能,我们将其嵌入到SSD框架中,设计了一个功能强大的端到端单级检测器LFBFR-SSD。在PASCAL VOC和MS COCO上进行的大量实验证明,我们的LFBFR-SSD在保持实时速度的同时,胜过许多最新的检测器。

更新日期:2021-02-16
down
wechat
bug