arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1909.09408cs.CV
收藏

ACFNet:用于语义分割的注意类别特征网络

ACFNet: Attentional Class Feature Network for Semantic Segmentation

Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所);University of Chinese Academy of Sciences(中国科学院大学);Baidu Inc.(百度公司)

Fan Zhang, Yanqin Chen, Zhihang Li, Zhibin Hong, Jingtuo Liu, Feifei Ma, Junyu Han, Errui Ding

摘要:

近年来的研究工作在语义分割方面取得了很大的进展,它们利用了更丰富的上下文,其中大部分是从空间角度设计的。与以往的工作相比,我们提出了类中心的概念,从范畴的角度提取全球范围内。这个类级上下文描述了图像中每个类的总体表示。我们进一步提出了一个新的模块,命名为注意力类别特征(ACF)模块,计算和自适应组合不同的类中心,根据每个像素。基于ACF模块,我们引入了一个由粗到细的分割网络,称为注意力类别特征网络(ACFNet),它可以由ACF模块和任何外壳分割网络(基础网络)组成。在本文中,我们使用两种类型的基础网络来评估ACFNet的有效性。我们在Cityscapes数据集上实现了81.85% mIoU的最新性能,仅使用精细注释的数据进行训练。

英文摘要:

Recent works have made great progress in semantic segmentation by exploiting richer context, most of which are designed from a spatial perspective. In contrast to previous works, we present the concept of class center which extracts the global context from a categorical perspective. This class-level context describes the overall representation of each class in an image. We further propose a novel module, named Attentional Class Feature (ACF) module, to calculate and adaptively combine different class centers according to each pixel. Based on the ACF module, we introduce a coarse-to-fine segmentation network, called Attentional Class Feature Network (ACFNet), which can be composed of an ACF module and any off-the-shell segmentation network (base network). In this paper, we use two types of base networks to evaluate the effectiveness of ACFNet. We achieve new state-of-the-art performance of 81.85% mIoU on Cityscapes dataset with only finely annotated data used for training.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑