当前位置: X-MOL 学术Neurocomputing › 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.)
BPFINet: Boundary-aware progressive feature integration network for salient object detection
Neurocomputing ( IF 6 ) Pub Date : 2021-04-24 , DOI: 10.1016/j.neucom.2021.04.078
Tianyou Chen , Xiaoguang Hu , Jin Xiao , Guofeng Zhang

Recently, convolutional neural networks have improved the results of salient object detection by a significant margin. Most existing methods focus on aggregating multi-level features but pay little attention to the differences between their spatial resolution. Besides, the widely used binary cross entropy loss treats all pixels equally and neglects the fact that pixels near the salient boundaries are prone to being misclassified. To solve these problems, we propose a novel network named BPFINet to aggregate low-level detail features, high-level semantic information, and global information progressively by using the U-shape Feature Integration Modules (UFIMs). Moreover, a U-shape Self-Refinement Module (USRM) is proposed to generate multi-scale representation from the intra-layer features and fuse them progressively to generate features robust to scale variation of salient objects. Besides, a Channel Compression Module (CCM) is designed to reduce the channel number of certain features and enhance the features by leveraging channel-wise attention. Furthermore, an integrated loss is introduced to highlight pixels near the salient boundaries and solve the problem caused by the imbalance of foreground and background regions. Experimental results on six benchmark datasets prove that our BPFINet is competitive compared with 16 other state-of-the-art methods. The source code will be publicly available at https://github.com/clelouch/BPFINet.



中文翻译:

BPFINet:边界感知渐进特征集成网络,用于显着物体检测

最近,卷积神经网络已显着提高了显着目标检测的结果。现有的大多数方法都集中于聚合多级要素,但很少注意其空间分辨率之间的差异。此外,广泛使用的二进制交叉熵损失均等地对待所有像素,而忽略了显着边界附近的像素容易被错误分类的事实。为了解决这些问题,我们提出了一种名为BPFINet的新型网络,该网络通过使用U形特征集成模块(UFIM)逐步聚合低级详细特征,高级语义信息和全局信息。而且,提出了一种U型自精整模块(USRM),以从层内特征生成多尺度表示并将其逐步融合,以生成对凸显对象的尺度变化具有鲁棒性的特征。此外,通道压缩模块(CCM)旨在减少某些功能的通道数量,并通过充分利用通道注意来增强功能。此外,引入了一种综合损失,以突出显示显着边界附近的像素,并解决了由前景和背景区域不平衡引起的问题。在六个基准数据集上的实验结果证明,与其他16个最新方法相比,我们的BPFINet具有竞争力。源代码将在https://github.com/clelouch/BPFINet上公开提供。通道压缩模块(CCM)旨在减少某些功能的通道数量,并通过充分利用通道注意来增强功能。此外,引入了一种综合损失,以突出显示显着边界附近的像素,并解决了由前景和背景区域不平衡引起的问题。在六个基准数据集上的实验结果证明,与其他16个最新方法相比,我们的BPFINet具有竞争力。源代码将在https://github.com/clelouch/BPFINet上公开提供。通道压缩模块(CCM)旨在减少某些功能的通道数量,并通过充分利用通道注意来增强功能。此外,引入了一种综合损失,以突出显示显着边界附近的像素,并解决了由前景和背景区域不平衡引起的问题。在六个基准数据集上的实验结果证明,与其他16个最新方法相比,我们的BPFINet具有竞争力。源代码将在https://github.com/clelouch/BPFINet上公开提供。在六个基准数据集上的实验结果证明,与其他16个最新方法相比,我们的BPFINet具有竞争力。源代码将在https://github.com/clelouch/BPFINet上公开提供。在六个基准数据集上的实验结果证明,与其他16个最新方法相比,我们的BPFINet具有竞争力。源代码将在https://github.com/clelouch/BPFINet上公开提供。

更新日期:2021-05-07
down
wechat
bug