Page 339 - 《软件学报》2020年第11期

3654 Journal of Software 软件学报 Vol.31, No.11, November 2020

4 结束语

本文提出一种基于图像级标注挖掘对象位置线索的弱监督图像分割方法.本文利用分类与分割共享的卷
积神经网络生成具有类别信息的注意力图,该注意力图能够挖掘出对象的判别性区域.同时,本文采用逐次擦除
法获取显著图,用于弥补注意力图丢失的对象空间位置信息,从而通过融合这两类信息生成伪像素标注并训练
分割网络模型.通过实验可以说明,有效的融合注意力图与显著图可以提高伪像素标注的质量,并且间接地提升
了弱监督分割的性能.通过在 PASCAL VOC 2012 数据集上与目前最先进的方法进行一系列的对比实验与分
析,我们发现,本文所提的方法具有较好的分割准确率.
弱监督图像语义分割具有很好的应用前景.未来的工作将针对注意力图和显著图做进一步改进,希望通过
图像的类别标签可以挖掘出更多的对象语义信息,进一步调整计算框架,并尝试应用于医学图像、遥感图像等
新的领域.

References:
[1] Jiang F, Gu Q, Hao HZ, Li N, Guo YW, Chen DX, Survey on content-based image segmentation methods. Ruan Jian Xue Bao/
Journal of Software, 2017,28(1):160−183 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/5136.htm [doi:
10.13328/j.cnki.jos.005136]
[2] LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proc. of the IEEE, 1998,
86(11):2278−2324. [doi: 10.1109/5.726791]
[3] Krizhevsky A, Sutskever I, Hinton GE. ImageNet: Classification with deep convolutional neural networks. In: Proc. of the
Advances in Neural Information Processing Systems. 2012. 1097−1105.
[4] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. In: Proc. of the Int’l Conf. on
Learning Representation. 2015.
[5] He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proc. of the IEEE Conf. on Computer Vision and
Pattern Recognition. 2016. 770−778.
[6] Huang G, Liu Z, van der Maate L, Weinberger KQ. Densely connected convolutional networks. In: Proc. of the IEEE Conf. on
Computer Vision and Pattern Recognition. 2017. 4700−4708.
[7] Bai C, Huang L, Chen JN, Pan X, Chen SY. Optimization of deep convolutional neural network for large scale image classification.
Ruan Jian Xue Bao/Journal of Software, 2018,29(4):1029−1038 (in Chinese with English abstract). http://www.jos.org.cn/1000-
9825/5404.htm [doi: 10.13328/j.cnki.jos.005404]
[8] Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation. In: Proc. of the IEEE Conf. on Computer
Vision and Pattern Recognition. 2015. 3431−3440.
[9] Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL. Semantic image segmentation with deep convolutional nets and fully
connected CRFS. In: Proc. of the Int’l Conf. on Learning Representation. 2015.
[10] Lin G, Milan A, Shen C, Reid I. RefineNet: Multi-path refinement networks for high-resolution semantic segmentation. In: Proc. of
the IEEE Conf. on Computer Vision and Pattern Recognition. 2017. 1925−1934.
[11] Hariharan B, Arbelaez P, Girshick R, Malik J. Hypercolumns for object segmentation and fine-grained localization. In: Proc. of the
IEEE Conf. on Computer Vision andPattern Recognition. 2015. 447−456.
[12] Mostajabi M, Yadollahpour P, Shakhnarovich G. Feedforward semantic segmentation with zoom-out features. In: Proc. of the IEEE
Conf. on Computer Vision and Pattern Recognition. 2015. 3376−3385.
[13] Hariharan B, Arbelaez P, Girshick R, Malik J. Simultaneous detection and segmentation. In: Proc. of the European Conf. on
Computer Vision. 2014. 297−312.
[14] Bearman A, Russakovsky O, Ferrari V, Li FF. What’s the point: Semantic segmentation with point supervision. In: Proc. of the
European Conf. on Computer Vision. 2016. 549−565.
[15] Xu J, Schwing AG, Urtasun R. Learning to segment under various forms of weak supervision. In: Proc. of the IEEE Conf. on
Computer Vision and Pattern Recognition. 2015. 3781−3790.
[16] Kolesnikov A, Lampert CH. Seed, expand and constrain: three principles for weaklysupervised image segmentation. In: Proc. of the
European Conf. on Computer Vision. 2016. 695−711.
[17] Vasconcelos M, Vasconcelos N, Carneiro G. Weakly supervised top-down image segmentation. In: Proc. of the IEEE Conf. on
Computer Vision and PatternRecognition. 2006. 1001−1006.