期刊
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
卷 30, 期 10, 页码 3372-3386出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCSVT.2019.2950526
关键词
Semantics; Feature extraction; Object detection; Proposals; Face detection; Convolution; Face; Object detection; multi-branch network; high-level semantic features; receptive field
资金
- Science and Technology Innovation 2030-Major Project of Artificial Intelligence of the Ministry of Science and Technology of China [2018AAA01028]
- National Natural Science Foundation of China [61632018, 61906131, 61936014, 61871470]
- Post-Doctoral Program for Innovative Talents [BX20180214]
- China Post-Doctoral Science Foundation [2018M641647]
To better solve scale variance problem, deep multi-scale methods usually detect objects of different scales by different in-network layers. However, the semantic levels of features from different layers are usually inconsistent. In this paper, we propose a multi-branch and high-level semantic network by gradually splitting a base network into multiple different branches. As a result, the different branches have same depth and the output features of different branches have similarly high-level semantics. Due to the difference of receptive fields, the different branches are suitable to detect objects of different scales. Meanwhile, the multi-branch network does not introduce additional parameters by sharing the convolutional weights of different branches. To further improve detection performance, skip-layer connections are used to add context to the branch of relatively small receptive field, and dilated convolution is incorporated to enlarge the resolutions of output feature maps. When they are embedded into Faster RCNN architecture, the weighted scores of proposal generation network and proposal classification network are further proposed. Experiments on three pedestrian datasets (i.e., the KITTI dataset, the Caltech dataset, and the Citypersons dataset), one face dataset (i.e., the WIDER FACE dataset), and two general object datasets (i.e., the COCO benchmark and the PASCAL VOC dataset) demonstrate the effectiveness and generality of proposed method. On these datasets, our method achieves state-of-the-art performance.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据