基于改进EMA单元的传统服饰图像语义分割

doi:10.13190/j.jbupt.2021-104

北京邮电大学学报 ›› 2022, Vol. 45 ›› Issue (1): 69-74.doi: 10.13190/j.jbupt.2021-104

基于改进EMA单元的传统服饰图像语义分割

赵海英, 朱会, 侯小刚

北京邮电大学人工智能学院, 北京 100876

收稿日期:2021-06-01 出版日期:2022-02-28 发布日期:2021-12-16
通讯作者: 侯小刚(1984—),男,博士生,邮箱:houxiaogang05@bupt.edu.cn E-mail:houxiaogang05@bupt.edu.cn
作者简介:赵海英(1972—),女,副教授
基金资助:
国家重点研发计划项目（2020YFF0305304）；北京邮电大学基本科研业务费项目（2020RC26）

Traditional Custume Image Semantic Segmentation Based on Improved EMA Unit

ZHAO Haiying, ZHU Hui, HOU Xiaogang

School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, China

Received:2021-06-01 Online:2022-02-28 Published:2021-12-16

摘要/Abstract

摘要： 针对传统服饰图像分割中标签易混淆和小目标易丢失带来的目标边缘细节难以保留等问题，提出了一种基于卷积注意力特征的残差期望最大化注意力语义分割网络模型。该模型首先以ResNeXt-50作为共享特征的主干网络，并通过在特征提取阶段引入一组平行的卷积注意力模块，可以有效地抑制无效特征，使目标区域的特征更加显著。然后利用残差思想对期望最大化注意力（EMA）单元进行优化，以解决迭代过程中梯度爆炸或者消失的问题，从而更好地建立特征图中位置间的关联，最终实现基于显著性融合学习的语义分割模型。最后在传统民族服饰数据集上通过定性与定量的实验验证了所提模型的有效性，其中平均交并比分割指标达到83.91%，取得了同类算法中最优效果。

关键词: 深度学习, 传统服饰, 特征提取, 注意力机制, 语义分割

Abstract: The object edge details are difficult to retain due to the confusion of labels and the loss of small objects in traditional clothing image segmentation. To solve the issue, a semantic segmentation network model termed residual expectation maximization attention based on convolution attention feature is proposed. The proposed model first uses ResNeXt-50 as the backbone network for shared features, and introduces a set of parallel convolutional attention modules in the feature extraction stage, which can effectively suppress invalid features and make the features of the target region more prominent. Then, the residual idea is used to optimize the expectation maximization attention unit to avoid the gradient explosion or disappearance in the iterative process, so as to establish the relationship between the positions in the feature map and realize the semantic segmentation model based on saliency fusion learning. Finally, qualitative and quantitative experiments verify the efficiency of the proposed model on the traditional national costume data set. The mean intersection over union segmentation index reaches 83.91%, which achieves the best results among similar algorithms.

Key words: deep learning, traditional costume, feature extraction, attention mechanism, semantic segmentation

中图分类号:

TP391.7

赵海英, 朱会, 侯小刚. 基于改进EMA单元的传统服饰图像语义分割[J]. 北京邮电大学学报, 2022, 45(1): 69-74.

ZHAO Haiying, ZHU Hui, HOU Xiaogang. Traditional Custume Image Semantic Segmentation Based on Improved EMA Unit[J]. Journal of Beijing University of Posts and Telecommunications, 2022, 45(1): 69-74.

参考文献

[1] OHTSU N. A threshold selection method from gray-level histograms[J]. IEEE Transactions on Systems Man and Cybernetics, 1979, 9(1):62-66.
[2] CHEN T S, XU M X, HUI X L, et al. Learning semantic-specific graph representation for multi-label image recognition[C]//Proceedings of the IEEE International Conference on Computer Vision. Seoul:IEEE, 2019:522-531.
[3] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(2):318-327.
[4] GONG Y C, JIA Y Q, LEUNG T, et al. Deep convolutional ranking for multilabel image annotation[C]//Proceedings of the International Conference on Learning Representations. Banff:ICLR, 2014:1-9.
[5] CHEN L C, PAPANDREOU G, KOKKINOS I, et al. Semantic image segmentation with deep convolutional nets and fully connected CRFs[C]//Proceeding of the International Conference on Learning Representations. San Diego:ICLR, 2015:357-361.
[6] XIE S, GIRSHICK R, DOLLÁR P, et al. Aggregated residual transformations for deep neural networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu:IEEE, 2017:5987-5995.
[7] WOO S, PARK J, LEE J Y, et al. Cbam:convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision. Munich:Springer Verlag, 2018:3-19.
[8] CHEN L C, PAPANDREOU G, KOKKINOS I, et al. Deeplab:semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 40(4):834-848.
[9] CHEN L C, ZHU Y K, PAPANDREOU G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//Proceedings of the European Conference on Computer Vision. Munich:Springer Verlag, 2018:801-818.
[10] ZHAO H S, SHI J P, QI X J, et al. Pyramid scene parsing network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu:IEEE, 2017:6230-6239.
[11] RONNEBERGER O, FISCHER P, BROX T. U-net:convolutional networks for biomedical image segmenta-tion[C]//Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention. Munich:Springer, 2015:234-241.
[12] BADRINARAYANAN V, KENDALL A, CIPOLLA R. Segnet:a deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(12):2481-2495.
[13] WANG X L, GIRSHICK R, GUPTA A, et al. Non-local neural networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake:IEEE, 2018:7794-7803.
[14] ZHAO H S, ZHANG Y, LIU S, et al. Psanet:point-wise spatial attention network for scene parsing[C]//Proceedings of the European Conference on Computer Vision. Munich:Springer Verlag, 2018:267-283.
[15] FU J, LIU J, TIAN H J, et al. Dual attention network for scene segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Long Beach:IEEE, 2019:3146-3154.
[16] HUANG Z L, WANG X G, HUANG L C, et al. CCNet:criss-cross attention for semantic segmentation[C]//Proceedings of the IEEE International Conference on Computer Vision. Seoul:IEEE, 2019:603-612.
[17] CHEN Y P, KALANTIDIS Y, LI J S, et al. A²-nets:double attention networks[C]//Proceedings of the Advances in Neural Information Processing Systems. Montreal:NeurIPS, 2019:350-359.
[18] LI X, ZHONG Z S, WU J L, et al. Expectation-maximization attention networks for semantic segmentation[C]//Proceedings of the IEEE International Conference on Computer Vision. Seoul:IEEE, 2019:9167-9176.
[19] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas:IEEE, 2016:770-778.
[20] WANG H Y, KEMBHAVI A, FARHADI A, et al. Elastic:improving CNNs with dynamic scaling policies[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Long Beach:IEEE, 2019:2258-2267.
[21] 侯小刚. 传统文化图案分割关键技术研究[D]. 北京:北京邮电大学, 2021:30-34.

基于改进EMA单元的传统服饰图像语义分割

Traditional Custume Image Semantic Segmentation Based on Improved EMA Unit

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	包乾辉文娟石淑珍董萌萍刘雪. 融合句法依存与 BERT-Att-BiLSTM 的属性分类[J]. 北京邮电大学学报, 2023, 46(4): 123-128.
[2]	刘阳, 滕颖蕾, 牛涛, 郅佳琳. 基于深度强化学习的滤波器剪枝方案[J]. 北京邮电大学学报, 2023, 46(3): 31-36.
[3]	靳梦凡, 黄智濒, 储志强. 复杂环境下多模态指导的点云补全方法[J]. 北京邮电大学学报, 2023, 46(3): 103-108.
[4]	胡敏熊思黄宏程张光华王春芳. 基于RAPNet的脑肿瘤MRI图像三维分割[J]. 北京邮电大学学报, 2023, 46(2): 91-97.
[5]	荣震宇刘建毅. 基于Transformer和MLP的眼底血管分割算法[J]. 北京邮电大学学报, 2023, 46(1): 26-31.
[6]	宋宇博高嘉振. 改进YOLOv3算法的交通多目标检测方法[J]. 北京邮电大学学报, 2022, 45(5): 103-108.
[7]	张小乾谈振王潇梁芹万黎明. 基于正交投影学习的图像特征提取算法[J]. 北京邮电大学学报, 2022, 45(5): 85-90,128.
[8]	刘金桐, 杨国兴, 刘晓鸿, 王光宇. 针对心电图分类模型的平滑攻击算法[J]. 北京邮电大学学报, 2022, 45(4): 44-50.
[9]	黄柳婷, 刘可欣, 牛凯, 常春, 贺志强. 基于深度学习的哮喘患者CT影像黏液栓自动识别[J]. 北京邮电大学学报, 2022, 45(4): 58-63.
[10]	刘琳岚, 宋修洋, 陈宇斌. 基于网络表示学习的机会网络链路预测[J]. 北京邮电大学学报, 2022, 45(4): 64-69,103.
[11]	宁静, 佘红艳, 赵东, 罗丹, 王磊. 一种路网级交通事故风险预测方法[J]. 北京邮电大学学报, 2022, 45(2): 72-78.
[12]	柳长源, 虎浩媛, 毕晓君. 双线性融合网络的驾驶员分心行为识别[J]. 北京邮电大学学报, 2022, 45(2): 79-84.
[13]	张滨宇, 赵衍运, 杜昀昊, 万俊峰, 佟知航. 一种基于深度学习的PCB图像字符检测方法[J]. 北京邮电大学学报, 2022, 45(1): 108-114.
[14]	贾珺, 冯春燕, 夏海轮, 张天魁, 李成钢. 基于样本均衡与特征交互的通信网络故障预测方法[J]. 北京邮电大学学报, 2021, 44(6): 59-66.
[15]	普运伟, 郭江, 刘涛涛, 吴海潇. 基于多学习单元卷积神经网络的雷达辐射源信号识别[J]. 北京邮电大学学报, 2021, 44(6): 74-82.