MDFN: Multi-scale deep feature learning network for object detection
MDFN: Multi-scale deep feature learning network for object detection
复制标题
DOI：
10.1016/j.patcog.2019.107149
复制
发表时间：
2020-04-01
影响因子：
8
通讯作者：
Wang, Guanghui
中科院分区：
文献类型：
--
作者：
Ma, Wenchi;Wu, Yuanwei;Wang, Guanghui
本文提出了一种创新的目标检测器，利用在高层学习到的深层特征。与早期层产生的特征相比，深层特征更能表达语义和上下文信息。所提出的深度特征学习方案将焦点从具有细节的具体特征转移到具有语义信息的抽象特征。它不仅考虑单个对象和局部上下文，还通过构建多尺度深度特征学习网络（MDFN）来考虑它们之间的关系。 MDFN通过在高层引入信息平方和立方初始模块来有效地检测目标，利用参数共享来提高计算效率。 MDFN通过集成多框、多尺度和多层次技术提供了多尺度目标检测器。尽管MDFN采用了具有相对较小的基础网络（VGG-16）的简单框架，但它比具有非常深或非常宽的宏观层次结构的框架获得了更好或有竞争力的检测结果，从而具有更强的特征提取能力。所提出的技术在 KITTI、PASCAL VOC 和 COCO 数据集上进行了广泛的评估，在 KITTI 上取得了最好的结果，在 PASCAL VOC 和 COCO 上取得了领先的性能。这项研究表明，深层特征提供了突出的语义信息和各种上下文内容，这有助于其在检测小或遮挡物体方面具有优越的性能。此外，MDFN模型计算效率高，在精度和速度之间做出了很好的权衡。 (C) 2019 Elsevier Ltd. 保留所有权利。
This paper proposes an innovative object detector by leveraging deep features learned in high-level layers. Compared with features produced in earlier layers, the deep features are better at expressing semantic and contextual information. The proposed deep feature learning scheme shifts the focus from concrete features with details to abstract ones with semantic information. It considers not only individual objects and local contexts but also their relationships by building a multi-scale deep feature learning network (MDFN). MDFN efficiently detects the objects by introducing information square and cubic inception modules into the high-level layers, which employs parameter-sharing to enhance the computational efficiency. MDFN provides a multi-scale object detector by integrating multi-box, multi-scale and multi-level technologies. Although MDFN employs a simple framework with a relatively small base network (VGG-16), it achieves better or competitive detection results than those with a macro hierarchical structure that is either very deep or very wide for stronger ability of feature extraction. The proposed technique is evaluated extensively on KITTI, PASCAL VOC, and COCO datasets, which achieves the best results on KITTI and leading performance on PASCAL VOC and COCO. This study reveals that deep features provide prominent semantic information and a variety of contextual contents, which contribute to its superior performance in detecting small or occluded objects. In addition, the MDFN model is computationally efficient, making a good trade-off between the accuracy and speed. (C) 2019 Elsevier Ltd. All rights reserved.