基于单点多盒检测器的全局-局部层级的域适应目标检测

doi:10.11772/j.issn.1001-9081.2020050622

计算机应用 ›› 2021, Vol. 41 ›› Issue (2): 517-522.DOI: 10.11772/j.issn.1001-9081.2020050622

所属专题：多媒体计算与计算机仿真

• 多媒体计算与计算机仿真 • 上一篇下一篇

基于单点多盒检测器的全局-局部层级的域适应目标检测

蒋宁^1,2, 方景龙¹, 杨庆³

1. 杭州电子科技大学计算机学院, 杭州 310018;
2. 宁波城市职业技术学院信息与智能工程学院, 浙江宁波 315110;
3. 南京工程学院计算机工程学院, 南京 211167

收稿日期:2020-05-23 修回日期:2020-08-03 出版日期:2021-02-10 发布日期:2020-08-26
通讯作者: 方景龙
作者简介:蒋宁(1974-),男,浙江宁波人,高级系统分析师,博士研究生,主要研究方向:人工智能、虚拟现实;方景龙(1964-),男,江西景德镇人,教授,博士,主要研究方向:人工智能、机器学习;杨庆(1976-),女,江苏南京人,副教授,博士,主要研究方向:虚拟仿真、图形图像。
基金资助:
浙江省教育厅科研项目（Y201533716）；江苏省科技计划项目（BY2016008-02）。

Global-local domain adaptive object detection based on single shot multibox detector

JIANG Ning^1,2, FANG Jinglong¹, YANG Qing³

1. School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou Zhejiang 310018, China;
2. School of Information and Intelligent Engineering, Ningbo City College of Vocational Technology, Ningbo Zhejiang 315110, China;
3. School of Computer Engineering, Nanjing Institute of Technology, Nanjing Jiangsu 211167, China

Received:2020-05-23 Revised:2020-08-03 Online:2021-02-10 Published:2020-08-26
Supported by:
This work is partially supported by the Scientific Research Project of Education Department of Zhejiang Province (Y201533716), the Science and Technology Program of Jiangsu Province (BY2016008-02).

摘要/Abstract

摘要： 在目标检测领域里通常希望在拥有大量标记的场景中训练好的模型能够应用在无标记的其他场景中，但是不同的域分布往往是不同的，这样往往导致域迁移时模型性能的急剧下降。为了提高域迁移时模型的目标检测性能，通过两个层级来解决域迁移问题，包括全局层级迁移和局部层级迁移。这两种层级迁移分别对应不同的特征对齐方式，即全局层级采用选择性对齐方式，局部层级采用完全对齐方式。所提域迁移框架基于单点多盒检测器（SSD）模型，在全局和局部层级分别配置相应的域适配器以减少域间差异，通过对抗网络算法实现具体训练，再通过一致性正则化来进一步提高模型的域迁移性能。通过大量实验验证了提出的域迁移模型的有效性，结果表明同目前常见的域适应-快速区域卷积（DA-FRCNN）模型、对抗识别域适应（ADDA）模型以及动态对抗适应网络（DAAN）模型等三种域迁移模型相比，该模型在不同数据集上的均值平均精度（mAP）可以提高5%~10%。

关键词: 目标检测, 域适配器, 域迁移, 对抗训练, 特征对齐, 卷积层, 损失函数, 单点多盒检测器

Abstract: In the field of object detection, it is hoped that the model trained in the domain with a lot of labels can be applied to other domains without labels, but different domain distributions are always different to each other, such difference will result in a sharp decline of model performance in domain transfer. To improve the model performance of object detection in domain transfer, the domain transfer was addressed on two levels, including the global-level transfer and the local-level transfer, which were corresponding to different feature alignment methods, that is, the global-level adopted selective alignment and the local-level adopted full alignment. The proposed domain transfer framework was constructed based on Single Shot MultiBox Detector (SSD) model and was disposed of two domain adaptors corresponding to global and local level respectively for the purpose of alleviating the domain difference. The specific training was implemented by the adversarial network algorithm, and the consistency regularization was used to further improve the domain transfer performance of the model. The effectiveness of the proposed domain transfer model was verified by many experiments. Experimental results show that on various datasets, the proposed model outperforms the existing common domain transfer models such as Domain Adaptation-Faster Region-based Convolutional Neural Network(DA-FRCNN), Adversarial Discriminative Domain Adaptation (ADDA), Dynamic Adversarial Adaptation Network (DAAN) by 5%-10% in term of mean Average Precision (mAP).

Key words: object detection, domain adaptor, domain transfer, adversarial training, feature alignment, convolution layer, loss function, Single Shot MultiBox Detector (SSD)

中图分类号:

TP391.9

蒋宁, 方景龙, 杨庆. 基于单点多盒检测器的全局-局部层级的域适应目标检测[J]. 计算机应用, 2021, 41(2): 517-522.

JIANG Ning, FANG Jinglong, YANG Qing. Global-local domain adaptive object detection based on single shot multibox detector[J]. Journal of Computer Applications, 2021, 41(2): 517-522.

参考文献

[1] BEN-DAVID S,BLITZER J,CRAMMER K,et al. A theory of learning from different domains[J]. Machine Learning,2010,79(1/2):151-175.
[2] BILEN H, VEDALDI H. Weakly supervised deep detection networks[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2016:2846-2854.
[3] LIU W,ANGUELOV D,ERHAN D,et al. SSD:single shot multibox detector[C]//Proceedings of the 2016 European Conference on Computer Vision,LNCS 9905. Cham:Springer, 2016:21-37.
[4] BEN-DAVID S, BLITZER J, CRAMMER K, et al. Analysis ofrepresentations for domain adaptation[C]//Proceedings of the 19th International Conference on Neural Information Processing Systems. Cambridge:MIT Press,2006:134-147.
[5] BUSTO P P, GALL J. Open set domain adaptation[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway:IEEE,2017:754-763.
[6] GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems. Cambridge:MIT Press,2014:2672-2680.
[7] DENG J,DONG W,SOCHER R,et al. ImageNet:a large-scale hierarchical image database[C]//Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2009:248-255.
[8] JIA Y,SHELHAMER E,DONAHUE J,et al. Caffe:convolutional architecture for fast feature embedding[C]//Proceedings of the 22nd ACM International Conference on Multimedia. New York:ACM,2014:675-678.
[9] 蔡国永, 贺歆灏, 储阳阳. 图像整体与局部区域嵌入的视觉情感分析[J]. 计算机应用,2019,39(8):2181-2185.(CAI G Y,HE X H,CHU Y Y. Visual sentiment analysis by combining global and local regions of image[J]. Journal of Computer Applications, 2019,39(8):2181-2185.)
[10] PAN S J,TSANG I W,KWORK J T,et al. Domain adaptation via transfer component analysis[J]. IEEE Transactions on Neural Networks,2011,22(2):199-210.
[11] GANIN Y,USTINOVA E,AJAKAN H,et al. Domain adversarial training of neural networks[J]. Journal of Machine Learning Research,2016,17(59):1-35.
[12] HE K,GKIOXARI G,DOLL′P,et al. Maximum independent domain adaptive[C]//Proceedings of the 2014 IEEE International Conference on Computer Vision. Piscataway:IEEE, 2014:781-792.
[13] HOFFMAN J,TZENG E,PARK T,et al. CyCADA:cycleconsistent adversarial domain adaptation[C]//Proceedings of the 35th International Conference on Machine Learning. New York:JMLR. org,2018:1989-1998.
[14] LONG M,WANG J,DING G,et al. Transfer feature learning with joint distribution adaptation[C]//Proceedings of the 2013 IEEE International Conference on Computer Vision. Piscataway:IEEE,2013:2200-2207.
[15] CORDTS M,OMRAN M,RAMOS S,et al. The cityscapes dataset for semantic urban scene understanding[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2016:3213-3223.
[16] FRENCH G,MACKIEWICZ M,FISHER M. Self-ensembling for visual domain adaptation[EB/OL].[2019-12-22]. https://arxiv.org/pdf/1706.05208.pdf.
[17] CHEN Y,LI W,SAKARIDIS C,et al. Domain adaptive fasterRCNN for object detection in the wild[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2018:3339-3348.
[18] TZENG E, HOFFMAN J, SAENKO K, et al. Adversarial discriminative domain adaptation[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2017:2962-2971.
[19] YU C,WANG J,CHEN Y,et al. Transfer learning with dynamic adversarial adaptation network[C]//Proceedings of the 2019 IEEE International Conference on Data Mining. Piscataway:IEEE, 2019:778-786.
[20] 陈龙杰, 张钰, 张玉梅, 等. 基于多注意力多尺度特征融合的图像描述生成算法[J]. 计算机应用,2019,39(2):354-359. (CHEN L J,ZHANG Y,ZHANG Y M,et al. Image caption generation algorithm based on multi-attention and multi-scale feature fusion[J]. Journal of Computer Applications,2019,39(2):354-359.)
[21] 郭川磊, 何嘉. 基于转置卷积操作改进的单阶段多边框目标检测方法[J]. 计算机应用,2018,38(10):2833-2838.(GUO C L,HE J. Improved single shot multibox detector based on the transposed convolution[J]. Journal of Computer Applications, 2018,38(10):2833-2838.)
[22] PEI Z, CAO Z, LONG M, et al. Multi-adversarial domain adaptation[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence. Palo Alto,CA:AAAI Press,2018:3934-3941.
[23] HOU S,WANG Z. Weighted channel dropout for regularization of deep convolutional neural network[C]//Proceedings of the 33rd AAAI Conference on Artificial Intelligence. Palo Alto,CA:AAAI Press,2019:8425-8432.

基于单点多盒检测器的全局-局部层级的域适应目标检测

Global-local domain adaptive object detection based on single shot multibox detector

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

[1]	马佳良, 陈斌, 孙晓飞. 基于改进的Faster R-CNN的通用目标检测框架[J]. 计算机应用, 2021, 41(9): 2712-2719.
[2]	徐江浪, 李林燕, 万新军, 胡伏原. 结合目标检测的室内场景识别方法[J]. 计算机应用, 2021, 41(9): 2720-2725.
[3]	樊玮, 李晨炫, 邢艳, 黄睿, 彭洪健. 航空发动机损伤图像的二分类到多分类递进式检测网络[J]. 计算机应用, 2021, 41(8): 2352-2357.
[4]	陈静, 毛莺池, 陈豪, 王龙宝, 王子成. 基于改进单点多盒检测器的大坝缺陷目标检测方法[J]. 计算机应用, 2021, 41(8): 2366-2372.
[5]	肖振远, 王逸涵, 罗建桥, 熊鹰, 李柏林. 基于部分加权损失函数的RefineDet[J]. 计算机应用, 2021, 41(7): 1928-1932.
[6]	侯笑晗, 金国栋, 谭力宁, 薛远亮. 基于自适应和最优特征的合成孔径雷达舰船检测方法[J]. 计算机应用, 2021, 41(7): 2150-2155.
[7]	王月, 江逸茗, 兰巨龙. 基于改进三元组网络和K近邻算法的入侵检测[J]. 计算机应用, 2021, 41(7): 1996-2002.
[8]	高钦泉, 黄炳城, 刘文哲, 童同. 基于改进CenterNet的竹条表面缺陷检测方法[J]. 计算机应用, 2021, 41(7): 1933-1938.
[9]	李朝, 兰海, 魏宪. 基于注意力的毫米波-激光雷达融合目标检测[J]. 计算机应用, 2021, 41(7): 2137-2144.
[10]	后云龙, 朱磊, 陈琴, 吕燧栋. 基于高斯差分特征网络的显著目标检测[J]. 计算机应用, 2021, 41(3): 706-713.
[11]	曹建荣, 吕俊杰, 武欣莹, 张旭, 杨红娟. 融合运动特征和深度学习的跌倒检测算法[J]. 计算机应用, 2021, 41(2): 583-589.
[12]	汪虹余, 张彧, 杨恒, 穆楠. 基于蚁群优化算法的弱光图像显著性目标检测[J]. 计算机应用, 2021, 41(10): 2970-2978.
[13]	裴仪瑶, 郭会明, 张丹普, 陈文博. 基于定位不确定性的鲁棒3D目标检测方法[J]. 计算机应用, 2021, 41(10): 2979-2984.
[14]	郑思诚, 孔令华, 游通飞, 易定容. 动态环境下基于深度学习的语义SLAM算法[J]. 计算机应用, 2021, 41(10): 2945-2951.
[15]	袁野, 谭晓阳. 复杂环境下的冰箱金属表面缺陷检测[J]. 计算机应用, 2021, 41(1): 270-274.