arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.01308cs.CV
收藏

CycleSegNet:基于循环细化和区域对应的对象共分割

CycleSegNet: Object Co-segmentation with Cycle Refinement and Region Correspondence

Nanyang Technological University(南洋理工大学);South China University of Technology(华南理工大学);Pazhou Lab(琶洲实验室);China University of Mining and Technology(中国矿业大学)

Chi Zhang, Guankai Li, Guosheng Lin, Qingyao Wu, Rui Yao

摘要:

图像联合分割是一种主动的计算机视觉任务,其目的是从一组图像中分割出共同的目标。近年来,研究者们设计了各种基于学习的算法来进行联合分割。该任务的主要困难在于如何有效地在图像之间传递信息以进行条件预测。在本文中,我们提出了CycleSegNet,一个新的框架的共同分割任务。我们的网络设计有两个关键组成部分:一个区域对应模块,这是局部图像区域之间交换信息的基本操作,以及一个循环细化模块,它利用ConvLSTM逐步更新图像表示并以循环和迭代的方式交换信息。大量的实验表明,我们提出的方法显着优于最先进的方法在四个流行的基准数据集- PASCAL VOC数据集,MSRC数据集,互联网数据集,iCoseg数据集,分别为2.6%,7.7%,2.2%和2.9%。

英文摘要:

Image co-segmentation is an active computer vision task that aims to segment the common objects from a set of images. Recently, researchers design various learning-based algorithms to undertake the co-segmentation task. The main difficulty in this task is how to effectively transfer information between images to make conditional predictions. In this paper, we present CycleSegNet, a novel framework for the co-segmentation task. Our network design has two key components: a region correspondence module which is the basic operation for exchanging information between local image regions, and a cycle refinement module, which utilizes ConvLSTMs to progressively update image representations and exchange information in a cycle and iterative manner. Extensive experiments demonstrate that our proposed method significantly outperforms the state-of-the-art methods on four popular benchmark datasets -- PASCAL VOC dataset, MSRC dataset, Internet dataset, and iCoseg dataset, by 2.6%, 7.7%, 2.2%, and 2.9%, respectively.

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。

↑