[1]蔡俊敏,孙 涵.基于注意力机制和多尺度特征的伪装目标检测[J].计算机技术与发展,2023,33(08):131-136.[doi:10. 3969 / j. issn. 1673-629X. 2023. 08. 019]
　CAI Jun-min,SUN Han.Camouflaged Object Detection Based on Attention Mechanism andMulti-scale Features[J].,2023,33(08):131-136.[doi:10. 3969 / j. issn. 1673-629X. 2023. 08. 019]
点击复制

基于注意力机制和多尺度特征的伪装目标检测()
分享到：

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

卷:
33
期数:
2023年08期
页码:
131-136
栏目:
人工智能
出版日期:
2023-08-10

文章信息/Info

Title:
Camouflaged Object Detection Based on Attention Mechanism andMulti-scale Features
文章编号:
1673-629X(2023)08-0131-06
作者:
蔡俊敏; 孙 涵
南京航空航天大学 计算机科学与技术学院 / 人工智能学院,江苏 南京 211106
Author(s):
CAI Jun-min; SUN Han
School of Computer Science and Technology / Artificial Intelligence,Nanjing University of Aeronautics and Astronautics,Nanjing 211106,China
关键词:
伪装目标检测; 注意力机制; 多尺度特征; 深度学习; 卷积神经网络
Keywords:
camouflaged object detection; attention mechanism; multi-scale feature; deep learning; convolutional neural network
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2023. 08. 019
摘要:
针对伪装目标结构多样、尺度不一和目标边界与其背景具有高度相似性的情况,提出了一种基于注意力机制和多尺度特征的伪装目标检测算法。 该算法主要分为两个部分,分别是基于多尺度特征的混合尺度解码器和基于反向注意力机制的注意力引导模块。 混合尺度解码器通过级联的特征融合单元,融合高层特征的语义信息与低层特征的空间细节信息,对特征编码器生成的特征金字塔进行解码,得到初步的检测结果;之后引入反向注意力机制,通过擦除图像中已经识别到的目标区域,来引导网络挖掘新的伪装线索,最终得到识别位置更准确、更完整的伪装目标。 实验中采用 COD10K 数据集、四种评价指标,与现有的十三种算法进行了对比。 实验结果表明,该伪装目标检测算法具有更好的性能表现。
Abstract:
An algorithm for detecting camouflaged objects based on attention mechanism and multi - scale features is proposed for thesituation that camouflaged objects have diverse structures, different scales and the object boundaries are highly similar to theirbackgrounds. The proposed algorithm is mainly divided into two parts,which are a mixed-scale decoder based on multi-scale featuresand an attention-guiding module based on the reverse attention mechanism. The mixed-scale decoder fuses the semantic information ofhigh-level features with the spatial detail information of low-level features through a cascaded feature fusion unit to decode the featurepyramid generated by the feature encoder and obtain the preliminary detection results. After that, the reverse attention mechanism isintroduced to guide the network to mine new camouflage cues by erasing the already recognized object regions in the image,and finallyobtain a more accurate and complete camouflage object. The COD10K dataset and four evaluation metrics are used in the experiments,and the comparison is conducted with thirteen existing algorithms. The experimental results show that the proposed algorithm has betterperformance.

相似文献/References:

[1]李梦洁,董峦.基于 PyTorch 的机器翻译算法的实现[J].计算机技术与发展,2018,28(10):160.[doi:10.3969/ j. issn.1673-629X.2018.10.033]
　LI Meng-jie,DONG Luan.Implementation of Machine Translation Algorithm Based on PyTorch[J].,2018,28(08):160.[doi:10.3969/ j. issn.1673-629X.2018.10.033]
[2]李东欣,禹 龙,田生伟,等.注意力机制的 LSTM-DBN 维语人称代词指代消解[J].计算机技术与发展,2019,29(07):33.[doi:10. 3969 / j. issn. 1673-629X. 2019. 07. 007]
　LI Dong-xin,YU Long,TIAN Sheng-wei,et al.Attention Mechanism of LSTM-DBN Uyghur Personal Pronoun Anaphora Resolution[J].,2019,29(08):33.[doi:10. 3969 / j. issn. 1673-629X. 2019. 07. 007]
[3]尹 鹏,周 林,郭 强,等.基于短语级注意力机制的关系抽取方法[J].计算机技术与发展,2019,29(09):24.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 005]
　YIN Peng,ZHOU Lin,GUO Qiang,et al.Relation Extraction Based on Phrase-level Attention[J].,2019,29(08):24.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 005]
[4]钟 诚,周浩杰,韦海亮.一种基于注意力机制的三维点云物体识别方法[J].计算机技术与发展,2020,30(04):41.[doi:10. 3969 / j. issn. 1673-629X. 2020. 04. 008]
　ZHONG Cheng,ZHOU Hao-jie,WEI Hai-liang.A 3D Point Cloud Object Recognition Method Based on Attention Mechanism[J].,2020,30(08):41.[doi:10. 3969 / j. issn. 1673-629X. 2020. 04. 008]
[5]王乾铭,李 吟.基于深度学习的个性化聊天机器人研究[J].计算机技术与发展,2020,30(04):79.[doi:10. 3969 / j. issn. 1673-629X. 2020. 04. 015]
　WANG Qian-ming,LI Yin.Research on Personalized Chatbot Based on Deep Learning[J].,2020,30(08):79.[doi:10. 3969 / j. issn. 1673-629X. 2020. 04. 015]
[6]朱立倩.基于深度学习的数显仪表字符识别[J].计算机技术与发展,2020,30(06):141.[doi:10. 3969 / j. issn. 1673-629X. 2020. 06. 027]
　ZHU Li-qian.Character Recognition of Digital Display Instrument Based on Deep Learning[J].,2020,30(08):141.[doi:10. 3969 / j. issn. 1673-629X. 2020. 06. 027]
[7]申静波,李井辉,孙丽娜.注意力机制在评论文本情感分析中的应用研究[J].计算机技术与发展,2020,30(07):169.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 036]
　SHEN Jing-bo,LI Jing-hui,SUN Li-na.Research on Application of Attention Mechanism in Comment Text Emotional Analysis[J].,2020,30(08):169.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 036]
[8]张亚飞.基于注意力的权重分配机制[J].计算机技术与发展,2020,30(09):49.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 009]
　ZHANG Ya-fei.Attention-based Weight Allocation Mechanism[J].,2020,30(08):49.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 009]
[9]王振业,叶成绪*,王文韬,等.基于 LSTM-Att 方法的音乐流行趋势预测[J].计算机技术与发展,2020,30(09):188.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 034]
　WANG Zhen-ye,YE Cheng-xu*,WANG Wen-tao,et al.Music Trend Forecast Based on LSTM-Att Method[J].,2020,30(08):188.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 034]
[10]陈 琛,刘小云,方玉华.融合注意力机制的电子病历命名实体识别[J].计算机技术与发展,2020,30(10):216.[doi:10. 3969 / j. issn. 1673-629X. 2020. 10. 038]
　CHEN Chen,LIU Xiao-yun,FANG Yu-hua.Named Entity Recognition in Electronic Medical Record Introducing Attention Mechanisms[J].,2020,30(08):216.[doi:10. 3969 / j. issn. 1673-629X. 2020. 10. 038]

更新日期/Last Update: 2023-08-10