A Multistage Refinement Network for Salient Object Detection

A Multistage Refinement Network for Salient Object Detection
复制标题

用于显着目标检测的多级细化网络

DOI:
10.1109/tip.2019.2962688
复制
发表时间:
2020-01
期刊:
IEEE Trans. Image Process.
影响因子:
--
通讯作者:
Lu Huchuan
Lu Huchuan
中科院分区:
其他
文献类型:
--
作者:
Zhang Lihe;Wu Jie;Wang Tiantian;Borji Ali;Wei Guohua;Lu Huchuan

文献摘要

参考文献

被引文献

相似文献

深度卷积神经网络(cnn)已经成功地应用于计算机视觉中的各种问题,包括显著目标检测。为了准确地检测和分割显著目标,需要同时提取和结合高级语义特征和低级精细细节。这对cnn来说是一个挑战,因为重复的子采样操作(如池化和卷积)会导致特征分辨率显著降低,从而导致空间细节和更精细的结构丢失。因此,我们提出了利用多阶段细化机制来增强前馈神经网络。在第一阶段,建立一个主网络来生成一个粗糙的预测图,其中大部分的详细结构是缺失的。在接下来的阶段中,配备与主网络分层循环连接的细化网络,以便跨阶段逐步组合本地上下文信息,以分阶段的方式细化前面的显著性图。在此基础上,利用金字塔池模块和通道关注模块对不同区域的全局上下文进行聚合。对六个基准数据集的广泛评估表明,所提出的方法优于最先进的方法。
Deep convolutional neural networks (CNNs) have been successfully applied to a wide variety of problems in computer vision, including salient object detection. To accurately detect and segment salient objects, it is necessary to extract and combine high-level semantic features with low-level fine details simultaneously. This is challenging for CNNs because repeated subsampling operations such as pooling and convolution lead to a significant decrease in the feature resolution, which results in the loss of spatial details and finer structures. Therefore, we propose augmenting feedforward neural networks by using the multistage refinement mechanism. In the first stage, a master net is built to generate a coarse prediction map in which most detailed structures are missing. In the following stages, the refinement net with layerwise recurrent connections to the master net is equipped to progressively combine local context information across stages to refine the preceding saliency maps in a stagewise manner. Furthermore, the pyramid pooling module and channel attention module are applied to aggregate different-region-based global contexts. Extensive evaluations over six benchmark datasets show that the proposed method performs favorably against the state-of-the-art approaches.
DOI: 10.1016/0010-0285(80)90005-5
发表时间: 1980-01-01
影响因子: 2.6
作者:
TREISMAN, AM;GELADE, G
通讯作者: GELADE, G
DOI: --
发表时间: 2016-12
期刊: ArXiv
影响因子: --
作者:
Marcel Simon;E. Rodner;Joachim Denzler
通讯作者: Marcel Simon;E. Rodner;Joachim Denzler
对应驱动的显着性转移
DOI: 10.1109/tip.2016.2601784
发表时间: 2016-11-01
影响因子: 10.6
作者:
Wang, Wenguan;Shen, Jianbing;Porikli, Fatih
通讯作者: Porikli, Fatih
DOI: 10.1109/tcsvt.2017.2706264
发表时间: 2018-10
影响因子: 8.4
作者:
Junwei Han;Gong Cheng;Zhenpeng Li;Dingwen Zhang
通讯作者: Junwei Han;Gong Cheng;Zhenpeng Li;Dingwen Zhang
DOI: 10.1109/cvpr.2018.00184
发表时间: 2018-06
期刊: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
影响因子: --
作者:
Wenguan Wang;Jianbing Shen;Xingping Dong;A. Borji
通讯作者: Wenguan Wang;Jianbing Shen;Xingping Dong;A. Borji