|
|
|
| Weakly supervised semantic segmentation based on category probability back propagation mechanism |
| Li Liangyu |
| College of Physics and Information Engineering, Fuzhou University, Fuzhou 350116 |
|
|
|
|
Abstract The bounding box with semantic information is used as the weak supervised annotations,and the object bounding box is used as a priori clue to find the feature points that belong to the target object but have weak activation value in the classification network. The correlation of the neuron nodes between the convolution layers is found by probability back propagation mechanism, and a complete class attention map of the object is obtained. In addition, by combining the image super-pixel algorithm, the rough dividing effect at the edge of the attention map is improved by the filling rate selection strategy, and the optimal category mask is generated. The extensive experiment results show that the method proposed method improves the integrity of the positioning of attention mechanism, and obtains 64.8% mIoU score results on the Pascal VOC2012 segmentation dataset.
|
|
Received: 29 October 2019
Published: 16 April 2020
|
|
|
|
| Cite this article: |
|
Li Liangyu. Weakly supervised semantic segmentation based on category probability back propagation mechanism[J]. Electrical Engineering, 2020, 21(4): 80-84.
|
|
|
|
| URL: |
|
http://dqjs.cesmedia.cn/EN/Y2020/V21/I4/80
|
[1] 黄旭超. 深度学习与电力智能化的思考[J]. 电气技术, 2018, 19(11): 1-4.
[2] 孙祥晟, 陈芳芳, 贾鉴, 等. 基于经验模态分解的神经网络光伏发电预测方法研究[J]. 电气技术, 2019, 20(8): 54-58.
[3] 王晓辉, 朱永利, 王艳, 等. 基于深度学习的电容器介损角在线辨识[J]. 电工技术学报, 2017, 32(15): 145-152.
[4] 王菲菲, 阮爱民, 魏刚, 等. 基于卷积神经网络的开关柜局部放电故障识别[J]. 电气技术, 2019, 20(4): 76-81.
[5] 金亮, 王飞, 杨庆新, 等. 永磁同步电机性能分析的典型深度学习模型与训练方法[J]. 电工技术学报, 2018, 33(增刊1): 41-48.
[6] 刘辉海, 赵星宇, 赵洪山, 等. 基于深度自编码网络模型的风电机组齿轮箱故障检测[J]. 电工技术学报, 2017, 32(17): 156-163.
[7] Long J, Shelhamer E, Darrell T.Fully convolutional networks for semantic segmentation[C]//Computer Vision and Pattern Recognition, 2015: 3431-3440.
[8] 李阳, 刘扬, 刘国军, 等. 基于对象位置线索的弱监督图像语义分割方法[J]. 软件学报, 2019-08-12. 基于对象位置线索的弱监督图像语义分割方法[J]. 软件学报, 2019-08-12. http:// kns.cnki.net/kcms/detail/11.2560.TP.20190812.1207.006.html[doi:10.13328/j.cnki.jos.005828]
[9] Papandreou G, Chen L C, Murphy K, et al. Weakly-and semi-supervised learning of a DCNN for semantic image segmentation[J]. arXiv preprint arXiv:1502. 02734, 2015.
[10] Krähenbühl P, Koltun V.Efficient inference in fully connected crfs with gaussian edge potentials[C]// Advances in neural information processing systems, 2011: 109-117.
[11] Dai J, He K, Sun J.Boxsup: exploiting bounding boxes to supervise convolutional networks for semantic segmentation[C]//Proceedings of the IEEE Inter- national Conference on Computer Vision, 2015: 1635-1643.
[12] Pont-Tuset J, Arbelaez P, Barron J T, et al.Multiscale combinatorial grouping for image segmentation and object proposal generation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 39(1): 128-140.
[13] Arbeláez P, Maire M, Fowlkes C, et al.Contour detection and hierarchical image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(5): 898-916.
[14] 熊昌镇, 智慧. 多模型集成的弱监督语义分割算法[J]. 计算机辅助设计与图形学学报, 2019, 31(5): 800-807.
[15] 熊昌镇, 智慧. 融合多尺度信息的弱监督语义分割及优化[J]. 通信学报, 2019, 40(1): 163-171. |
|
|
|
2020, Vol. 21 
