[1]仲林伟,陈丹伟.结合循环提取器与自蒸馏的目标检测方法[J].计算机技术与发展,2024,34(04):70-75.[doi:10. 3969 / j. issn. 1673-629X. 2024. 04. 011]
　ZHONG Lin-wei,CHEN Dan-wei.An Object Detection Method Combining Circular Extractor and Self Distillation[J].,2024,34(04):70-75.[doi:10. 3969 / j. issn. 1673-629X. 2024. 04. 011]
点击复制

结合循环提取器与自蒸馏的目标检测方法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
34
期数:
2024年04期
页码:
70-75
栏目:
媒体计算
出版日期:
2024-04-10

文章信息/Info

Title:
An Object Detection Method Combining Circular Extractor and Self Distillation
文章编号:
1673-629X(2024)04-0070-06
作者:
仲林伟; 陈丹伟
南京邮电大学 计算机学院,江苏 南京 210003
Author(s):
ZHONG Lin-wei; CHEN Dan-wei
School of Computer Science,Nanjing University of Posts and Telecommunications,Nanjing 210003,China
关键词:
深度学习; 目标检测; 特殊天气; 循环解纠缠; 自蒸馏; 域不变特征
Keywords:
deep learning; object detection; adverse weather; cyclic-disentangled; self-distillation; domain-invariant representations
分类号:
TP391. 41
DOI:
10. 3969 / j. issn. 1673-629X. 2024. 04. 011
摘要:
在深度学习时代,目标检测方法不断发展,且在良好的视觉环境中已经具有较高的水平。 但是,在特殊天气下,常规的目标检测方法的检测性能大幅下降,甚至失效,而特殊天气环境的行车安全一直是社会广泛关注的问题。 为了解决上述问题,该文主要设计了一个目标检测器的模型,即引入循环解纠缠、自蒸馏方法的改进 YOLO 模型。 在循环解纠缠模块,从输入图像中循环提取域不变特征,通过循环操作,可以在不依赖域相关注释的情况下,提高图像域特征和域不变特征的解缠能力;在自蒸馏模块,以提取到的域不变特征为教师对象,进一步提高泛化能力。 并且该检测器在只有一个源域进行训练的情况下,面对许多未曾训练过的目标域上仍然表现良好,提高了检测器在未知域的鲁棒性。 实验验证了模型在各种天气下城市场景目标检测的效果,实验数据表明,该方法优于基线约 8 百分点,相比基线方法获得了性能提升。
Abstract:
In the era of deep learning,object detection methods are constantly developing and have reached a high level in a good visualenvironment. However,the detection performance?
of conventional target detection methods in adverse weather conditions has significantlydecreased or even failed,and driving safety in adverse weather environments has always been a widespread concern in society. In order tosolve the above problems,we mainly design a model of the target detector,which is an improved YOLO model that introduces cyclic-disentanglement and self-distillation methods. In the cyclic disentanglement module,domain invariant features are extracted from the inputimage in a cyclic manner. Through cyclic operations,the ability to unwrap image domain features and domain invariant features can beimproved without relying on domain related annotations; in the self-distillation module,the extracted domain invariant features are usedas the teacher’s object to further improve generalization ability. Moreover,the detector performs well in many untrained target domainseven when trained in only one source domain, improving its robustness in the unknown domain. The experiment verifies the effectivenessof the model in detecting urban scene targets under various weather conditions. The experimental data show that the proposed methodoutperforms the baseline by about 8 percentage points and achieves performance improvement compared to the baseline method.

相似文献/References:

[1]刘晓明 李毓蕙 高燕 郑华强.基于目标区域清晰显示的H.264编码策略[J].计算机技术与发展,2010,(06):29.
　LIU Xiao-ming,LI Yu-hui,GAO Yan,et al.A Coding Strategy of H.264 Based on High-definition Display of Target Region[J].,2010,(04):29.
[2]刘翔 吴谨 祝愿博 康晓晶.基于视频序列的目标检测与跟踪技术研究[J].计算机技术与发展,2009,(11):179.
　LIU Xiang,WU Jin,ZHU Yuan-bo,et al.A Study of Object Detecting and Tracking Based on Video Sequences[J].,2009,(04):179.
[3]曙光 张超 蔡则苏.基于改进的混合高斯模型的目标检测方法[J].计算机技术与发展,2012,(07):60.
　SHU Guang,ZHANG Chao,CAI Ze-su.Target Detection Method Based on Improved Gaussian Mixture Model[J].,2012,(04):60.
[4]刘洁,李目,周少武.一种混沌混合粒子群优化RBF神经网络算法[J].计算机技术与发展,2013,(08):181.
　LIU Jie[],LI Mu[],ZHOU Shao-wu[].An Algorithm of Chaotic Hybrid Particle Swarm Optimization Based on RBF Neural Network[J].,2013,(04):181.
[5]蒋翠清,孙富亮,吴艿芯. 基于相对欧氏距离的背景差值法视频目标检测[J].计算机技术与发展,2015,25(01):37.
　JIANG Cui-qing,SUN Fu-liang,WU Nai-xin. Video Object Detection of Background Subtraction Method Based on Relative Euclidean Distance[J].,2015,25(04):37.
[6]卢官明,衣美佳. 步态识别关键技术研究[J].计算机技术与发展,2015,25(07):100.
　LU Guan-ming,YI Mei-jia. Research on Critical Techniques in Gait Recognition[J].,2015,25(04):100.
[7]高翔,朱婷婷,刘洋. 多摄像头系统的目标检测与跟踪方法研究[J].计算机技术与发展,2015,25(07):221.
　GAO Xiang,ZHU Ting-ting,LIU Yang. Research of Target Detection and Tracking Method for Multi-camera System[J].,2015,25(04):221.
[8]章文洁[][],黄旻[],张桂峰[]. 滤光片多光谱成像中运动目标场景误配准修正[J].计算机技术与发展,2016,26(01):18.
　ZHANG Wen-jie[][],HUANG Min[],ZHANG Gui-feng[]. Misregistration Correction for Moving Object Scene in Filter-type Multispectral Imaging[J].,2016,26(04):18.
[9]陈强锐,谢世朋.基于深度学习的肺部肿瘤检测方法[J].计算机技术与发展,2018,28(04):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
　CHEN Qiang-rui,XIE Shi-peng.Lung Cancer Detection Method Based on Deep Learning[J].,2018,28(04):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
[10]黄法秀,张世杰,吴志红,等.数据增广下的人脸识别研究[J].计算机技术与发展,2020,30(03):67.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 013]
　HUANG Fa-xiu,ZHANG Shi-jie,WU Zhi-hong,et al.Research on Face Recognition Based on Data Augmentation[J].,2020,30(04):67.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 013]
[11]施泽浩,赵启军.基于全卷积网络的目标检测算法[J].计算机技术与发展,2018,28(05):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
　SHI Ze-hao,ZHAO Qi-jun.Object Detection Algorithm Based on Fully Convolutional Neural Network[J].,2018,28(04):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
[12]丁洪金,宫法明.基于时序分析的人体活动状态识别与定位[J].计算机技术与发展,2019,29(04):82.[doi:10. 3969 / j. issn. 1673-629X. 2019. 04. 017]
　DING Hong-jin,GONG Fa-ming.Human Activities Recognition and Location Based on Temporal Analysis[J].,2019,29(04):82.[doi:10. 3969 / j. issn. 1673-629X. 2019. 04. 017]
[13]陈莉君,李 卓.基于深度神经压缩的 YOLO 优化[J].计算机技术与发展,2019,29(12):72.[doi:10. 3969 / j. issn. 1673-629X. 2019. 12. 013]
　CHEN Li-jun,LI Zhuo.YOLO Optimization Based on Deep Neural Compression[J].,2019,29(04):72.[doi:10. 3969 / j. issn. 1673-629X. 2019. 12. 013]
[14]许必宵,宫 婧,孙知信.基于卷积神经网络的目标检测模型综述[J].计算机技术与发展,2019,29(12):87.[doi:10. 3969 / j. issn. 1673-629X. 2019. 12. 016]
　XU Bi-xiao,GONG Jing,SUN Zhi-xin.A Survey of Object Detection Models Based on Convolutional Neural Networks[J].,2019,29(04):87.[doi:10. 3969 / j. issn. 1673-629X. 2019. 12. 016]
[15]徐 融,邱晓晖.一种改进的 YOLO V3 目标检测方法[J].计算机技术与发展,2020,30(07):30.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 007]
　XU Rong,QIU Xiao-hui.An Improved YOLO V3 Object Detection[J].,2020,30(04):30.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 007]
[16]宫法明,马玉辉.基于时空双分支网络的人体动作识别研究[J].计算机技术与发展,2020,30(09):23.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 005]
　GONG Fa-ming,MA Yu-hui.Research on Human Action Recognition Based on Space-time Double-branch Network[J].,2020,30(04):23.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 005]
[17]何 松,孙 静,郭乐江,等.基于激光 SLAM 和深度学习的语义地图构建[J].计算机技术与发展,2020,30(09):88.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 016]
　HE Song,SUN Jing,GUO Le-jiang,et al.Semantic Mapping Based on Laser SLAM and Deep Learning[J].,2020,30(04):88.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 016]
[18]余 进,史燕中,王春华,等.一种轻量化目标检测算法研究[J].计算机技术与发展,2020,30(11):42.[doi:10. 3969 / j. issn. 1673-629X. 2020. 11. 008]
　YU Jin,SHI Yan-zhong,WANG Chun-hua,et al.Research of a Lightweight Object Detection Algorithm[J].,2020,30(04):42.[doi:10. 3969 / j. issn. 1673-629X. 2020. 11. 008]
[19]樊海玮,史 双,蔺 琪,等.复杂背景下 SAR 图像船舶目标检测算法研究[J].计算机技术与发展,2021,31(10):49.[doi:10. 3969 / j. issn. 1673-629X. 2021. 10. 009]
　FAN Hai-wei,SHI Shuang,LIN Qi,et al.Research on Ship Target Detection Algorithm in Complex Background SAR Image[J].,2021,31(04):49.[doi:10. 3969 / j. issn. 1673-629X. 2021. 10. 009]
[20]李 威,李 楠,于清玲.基于 Faster RCNN 的可回收物自动分类算法研究[J].计算机技术与发展,2021,31(增刊):100.[doi:10. 3969 / j. issn. 1673-629X. 2021. S. 020]
　LI Wei,LI Nan,YU Qing-ling.Research on Automatic Classification Algorithm of Recyclables Based on Faster RCNN[J].,2021,31(04):100.[doi:10. 3969 / j. issn. 1673-629X. 2021. S. 020]

更新日期/Last Update: 2024-04-10