CACNet: Salient object detection via context aggregation and contrast embedding

CACNet: Salient object detection via context aggregation and contrast embedding
复制标题

CACNet:通过上下文聚合和对比嵌入进行显着对象检测

DOI:
10.1016/j.neucom.2020.04.032
复制
发表时间:
2020-08
期刊:
影响因子:
6
通讯作者:
Lu Huchuan
Lu Huchuan
中科院分区:
计算机科学2区
文献类型:
--
作者:
Feng Guang;Bo Hongguang;Sun Jiayu;Zhang Lihe;Lu Huchuan

文献摘要

参考文献

相似文献

近年来,如何在卷积神经网络(CNN)中自适应地挖掘最有用的上下文信息一直是显著性检测任务面临的最紧迫的问题之一。在本文中,我们提出了一种新的上下文特征聚合网络与边界对比度嵌入(CACNet)灵活地集成上下文信息,而不受卷积滤波器的固定几何结构的影响。我们采用了一个细节增强模块(DEM),使网络更加关注图像结构的变化。一个上下文自适应聚合模块(CA2M)也被用来选择性地整合特征地图的上下文信息。此外,边界对比度损失函数(BCL)通过最大化边界像素之间的特征差异来增强学习特征的可辨别性。在五个基准数据集上的实验表明,该方法在不同的评价指标下优于其他最先进的方法。在测试阶段,网络可以以大约36 FPS的速度运行,并且不需要任何后处理。
Recently, how to adaptively exploring the most useful context information in Convolutional Neural Networks (CNNs) has been one of the most pressing problems facing the saliency detection task. In this paper, we propose a novel Context Feature Aggregation Network with Boundary Contrast Embedding (CACNet) to flexibly integrate context information without being affected by the fixed geometric structures of convolution filters. We adopt a Detail Enhancement Module (DEM) to make the network pay greater attention to the changes of image structure. A Context Adaptive Aggregation Module (CA2M) is also employed to selectively integrate the context information of the feature map. Moreover, a Boundary Contrast Loss function (BCL) enhances the discriminability of learned features by maximizing feature differences between boundary pixels. Extensive experiments on five benchmark datasets demonstrate that the proposed method outperforms other state-of-the-art methods under different evaluation metrics. During the testing stage, the network can run at about 36 FPS and does not need any post-processing.
DOI: 10.1007/s11263-017-1004-z
发表时间: 2017-12-01
影响因子: 19.5
作者:
Xie, Saining;Tu, Zhuowen
通讯作者: Tu, Zhuowen
DOI: --
发表时间: 2015-02
期刊: --
影响因子: --
作者:
Seunghoon Hong;Tackgeun You;Suha Kwak;Bohyung Han
通讯作者: Seunghoon Hong;Tackgeun You;Suha Kwak;Bohyung Han
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
DOI: 10.1109/tip.2012.2202676
发表时间: 2013-01-01
影响因子: 10.6
作者:
Gao, Yue;Wang, Meng;Wu, Xindong
通讯作者: Wu, Xindong
DOI: 10.1109/cvpr.2009.5206596
发表时间: 2009-06
期刊: 2009 IEEE Conference on Computer Vision and Pattern Recognition
影响因子: --
作者:
R. Achanta;S. Hemami;F. Estrada;S. Süsstrunk
通讯作者: R. Achanta;S. Hemami;F. Estrada;S. Süsstrunk