基于多级特征融合的伪装目标分割

doi:10.3778/j.issn.1002-8331.2201-0412

摘要/Abstract

摘要： 在伪装目标分割任务中，如何提取深度模型下高分辨率的目标语义特征是构建目标分割模型的关键。针对此问题，提出了一种基于多级特征融合的伪装目标分割方法。在特征编码过程中，引入多级门控模块对Res2Net-50的多级中间层特征进行选择性融合，有效过滤各级特征图的干扰信息；在解码过程中，通过自交互残差模块驱动不同尺度的编码特征实现交叉融合，获得更准确的目标表示信息。此外，在交叉熵损失的基础上加入Dice损失形成联合损失函数，帮助模型更精准地分割伪装目标。实验结果证明，在背景复杂的迷彩伪装数据集以及三个常用自然伪装数据集上，相比其他典型模型，该模型表现出更好的分割效果。

关键词: 深度学习, 伪装目标分割, 特征融合, 门控机制, 多尺度特征

Abstract: In the field of camouflaged object segmentation, how to extract high-resolution semantic features from a depth model is the key to constructing a target segmentation model. In order to better solve this problem, a new camouflage target segmentation method based on multi-level feature fusion is proposed. A multi-stage gate control module is introduced to selectively fuse the multi-stage middle layer features of Res2Net-50, which can effectively filter the interference information of each level feature map during the feature encoding process. And in decoding, the self-interaction residual module has been used to drive the cross-fusion of encoding features of different scales, which guarantees the obtaining of more accurate target representation information. In addition, this paper combines cross entropy loss and Dice loss as a joint loss function to help the model segment the camouflaged target more accurately. Experimental results show that the proposed model performs better than the other eight typical models in the complex background camouflage data set and three common natural camouflage datasets.

Key words: deep learning, camouflaged object segmentation, feature fusion, gating mechanism, multiscale feature

付炳阳, 曹铁勇, 郑云飞, 方正, 王杨, 王烨奎. 基于多级特征融合的伪装目标分割[J]. 计算机工程与应用, 2022, 58(18): 268-276.

FU Bingyang, CAO Tieyong, ZHENG Yunfei, FANG Zheng, WANG Yang, WANG Yekui. Multi-Feature Fusion for Camouflaged Object Segmentation[J]. Computer Engineering and Applications, 2022, 58(18): 268-276.

参考文献

[1] FAN D P，JI G P，CHENG M M，et al.Concealed object detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2021：2777-2787.
[2] TANKUS A，YESHURUN Y.Convexity-based visual camouflage breaking[J].Computer Vision and Image Understanding，2001，82（3）：208-237.
[3] NAGAPPA U，NAGABHUSAN P.Camouflage defect identification：a novel approach[C]//Proceedings of the 9th International Conference on Information Technology.Bhubaneswar，India：IEEE，2006：145-148.
[4] SENGOTTUVELAN P，AMITABH W，SHANMUGAM A.Performance of decamouflaging through exploratory image analysis[C]//Proceedings of the 2008 First International Conference on Emerging Trends in Engineering and Technology.Nagpur，India：IEEE，2008：6-10.
[5] 王勇智.基于图像处理的变形迷彩目标发现研究[D].重庆：重庆大学，2009.
WANG Y Z.Study on deformation-camouflage target discovery based on image processing[D].Chongqing：Chongqing University，2009.
[6] 鲜晓东，李克文.基于颜色和纹理特征的伪装色矿工目标检测[J].计算机应用，2013，33（2）：539-542.
XIAN X D，LI K W.Detection of camouflaged miner objects based on color and texture features[J].Journal of Computer Applications，2013，33（2）：539-542.
[7] LI C，ZHAO X，WAN Y.The camouflage color object detection with deep networks[C]//Proceedings of the 2017 International Conference on Neural Information Processing.Guangzhou，China：Springer，2017：476-485.
[8] ZHENG Y F，ZHANG X Y，WANG F，et al.Detection of people with camouflage pattern via dense deconvolution network[J].IEEE Signal Processing Letters，2018，26（1）：29-33.
[9] 卓刘，陈晓琪，谢振平，等.基于深度神经网络的迷彩目标发现仿真学习方法[J].激光与光电子学进展，2019，56（7）：154-160.
ZHUO L，CHEN X Q，XIE Z P，et al.Simulation learning method for discovery of camouflage targets based on deep neural networks[J].Laser & Optoelectronics Progress，2019，56（7）：154-160.
[10] LE T N，NGUYEN T V，NIE Z，et al.Anabranch network for camouflaged object segmentation[J].Computer Vision and Image Understanding，2019，184（1）：45-46.
[11] FANG Z，CAO T Y，ZHANG X Y，et al.Camouflage people detection via strong semantic dilation network[C]//Proceedings of the ACM Turing Celebration Conference.Chengdu，China：IEEE，2019：1-7.
[12] YAN J，LE T N，NGUYEN K D，et al.Mirrornet：bio-inspired adversarial attack for camouflaged object segmentation[J].IEEE Access，2021，9（1）：43290-43300.
[13] MEI H，JI G P，WEI Z Q，et al.Camouflaged object segmentation with distraction mining[EB/OL].[2021-04-21].https：//arxiv.org/pdf/2104.10475.pdf.
[14] ZHAI Q，LI X，YANG F，et al.202 mutual graph learning for camouflaged object detection[EB/OL].[2021-04-03].https：//arxiv.org/pdf/2104.02613.pdf.
[15] GAO S，CHENG M M，ZHAO K，et al.Res2net：a new multi-scale backbone architecture[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2019，43（2）：652-662.
[16] LONG J，SHELHAMER E，DARRELL T.Fully convolutional networks for semantic segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2015，39（4）：640-651.
[17] ZHANG P，WANG D，LU H，et al.Amulet：agregating multi-level convolutional features for salient object detection[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision.Venice，Italy：IEEE，2017：202-211.
[18] LUO Z，MISHRA A，ACHKAR A，et al.Non-local deep features for salient object detection[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition.Hawaii，USA：IEEE，2017.
[19] TAKIKAWA T，ACUNA D，JAMPANI V，et al.Gated-SCNN：gated shape CNNs for semantic segmentation[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision（ICCV）.Seoul，Korea：IEEE，2019：5228-5237.
[20] SUN K，XIAO B，LIU D，et al.Deep high-resolution representation learning for human pose estimation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2019：5693-5703.
[21] WEI J，WANG S，HUANG Q.F3net：fusion，feedback and focus for salient object detection[J].Artificial Intelligence，2019，34（7）：12321-12328.
[22] MILLETARI F，NAVAB N，AHMADI S A.V-Net：fully convolutional neural networks for volumetric medical image segmentation[C]//Proceedings of the 2016 Fourth International Conference on 3D Vision（3DV）.California，USA：IEEE，2016：565-571.
[23] SKUROWSKI P，ABDULAMEER H，B?ASZCZYK J，et al.Animal camouflage analysis：chameleon database[EB/OL].[2018].http：//kgwisc.aei.polsl.pl/index.php/en/dataset/63-animal-camouflage-analysis.
[24] FAN D P，CHENG M M，LIU Y，et al.Structure-measure：a new way to evaluate foreground maps[J].International Journal of Computer Vision，2017，129（9）：2622-2638.
[25] FAN D P，JI G P，QIN X B，et al.Structure-measure：a new way to evaluate foreground maps[J].Scientia Sinica Informationis，2021，51（9）：1475-1476.
[26] RAN M，ZELNIKMANOR L，TAL A.How to evaluate foreground maps[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition.Columbus，OH，USA：IEEE，2014：248-255.
[27] FAN D P，JI G P，ZHOU T，et al.PraNet：parallel reverse attention network for polyp segmentation[C]//Proceedings of the Medical Image Computing and Computer Assisted Intervention.Lima Peru：IEEE，2020：263-273.
[28] CHEN Z，XU Q，CONG R，et al.Global context-aware progressive aggregation network for salient object detection[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2020：10599-10606.
[29] PANG Y，ZHAO X，ZHANG L，et al.Multi-scale interactive network for salient object detection[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Seattle，WA，USA：IEEE，2020：9410-9419.
[30] WU Z，SU L，HUANG Q.Cascaded partial decoder for fast and accurate salient object detection[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Long Beach，CA，USA：IEEE，2019：3902-3911.