融合特征增强和自注意力的SSD小目标检测算法

doi:10.3778/j.issn.1002-8331.2109-0356

摘要/Abstract

摘要： SSD是一种多尺度目标检测算法，由于浅层特征图缺乏语义信息，导致小目标的检测准确率低。针对这个问题，提出一种融合特征增强和自注意力的SSD小目标检测算法FA-SSD。该算法在SSD基础上构建一条自深向浅的递归反向路径，此路径包含三个模块：深层特征增强模块利用路径深层多尺度特征图生成的上下文信息和最深层特征图的语义信息，增强深层特征信息的表达能力；上采样特征增强模块通过扩大特征图的感受野，增强反向路径中上采样特征图的语义信息；自适应特征融合模块引入自注意力机制自适应地融合相邻的浅层特征图和上采样特征图，生成新的具有强语义和精确位置信息的特征图。实验结果显示，在PASCAL VOC和TT100K数据集上，FA-SSD的mAP最高达到了92.5%和80.2%，表明该检测算法能够增强浅层特征图的语义信息，对于复杂场景下的小目标有着较好的检测效果。

关键词: 小目标检测, 特征增强, 自注意力机制, 特征融合, 上下文信息

Abstract: SSD is a multi-scale target detection algorithm. Due to the lack of semantic information in shallow feature images, the detection accuracy of small targets is low. To solve this problem, a SSD small target detection algorithm, FA-SSD, which combines feature enhancement and self-attention, is proposed. The algorithm constructs a recursive reverse path from deep to shallow based on SSD, which consists of three modules：the deep feature enhancement module uses the contextual information generated from the deep multi-scale feature map and the semantic information of the deepest feature map to enhance the expression ability of the deep feature information; the up-sampling feature enhancement module enhances the semantic information of the up-sampling feature map in the reverse path by enlarging the receptive field of the feature map. The adaptive feature fusion module adaptively fuses adjacent shallow feature images and up-sampling feature images with self-attention mechanism to generate new feature images with strong semantic and precise location information. Experimental results show that on PASCAL VOC and TT100K datasets, the mAP of FA-SSD is up to 92.5% and 80.2%, indicating that this algorithm can enhance the semantic information of shallow feature images and has a good detection effect on small targets in complex scenes.

Key words: small target detection, feature enhancement, self-attention mechanism, feature fusion, context information

张馨月, 降爱莲. 融合特征增强和自注意力的SSD小目标检测算法[J]. 计算机工程与应用, 2022, 58(5): 247-255.

ZHANG Xinyue, JIANG Ailian. SSD Small Target Detection Algorithm Combining Feature Enhancement and Self-Attention[J]. Computer Engineering and Applications, 2022, 58(5): 247-255.

参考文献

[1] 梁鸿，王庆玮，张千，等.小目标检测技术研究综述[J].计算机工程与应用，2021，57（1）：17-28.
LIANG H，WANG Q W，ZHANG Q，et al.Small object detection technology：a review[J].Computer Engineering and Applications，2021，57（1）：17-28.
[2] 赵军艳，降爱莲，强彦.YOLOv3融合图像超分辨率重建的鲁棒人脸检测[J/OL].计算机工程与应用：1-9[2021-08-30].http：//kns.cnki.net/kcms/detail/11.2127.TP.20210420.1527.
087.html.
ZHAO J Y，JIANG A L，QIANG Y.Robust face detection using YOLOv3 fusion super resolution reconstruction[J/OL].Computer Engineering and Applications：1-9[2021-08-30].http：//kns.cnki.net/kcms/detail/11.2127.TP.20210420.1527.
087.html.
[3] TOBG K，WU Y，ZHOU F.Recent advances in small object detection based on deep learning：a review[J].Image and Vision Computing，2020，97：103910.
[4] REDMON J，FARHADI A.Yolov3：an incremental improvement[J].arXiv：1804.02767，2018.
[5] LIU W，ANGUELOV D，ERHAN D，et al.SSD：single shot multibox detector[C]//European Conference on Computer Vision.Cham：Springer，2016：21-37.
[6] FU C Y，LIU W，RANGA A，et al.DSSD：deconvolutional single shot detector[J].arXiv：1701.06659，2017.
[7] CUI L，MA R，LV P，et al.MDSSD：multi-scale deconvolutional single shot detector for small objects[J].Science China（Information Sciences），2020，63（2）：94-96.
[8] 梁延禹，李金宝.多尺度非局部注意力网络的小目标检测算法[J].计算机科学与探索，2020，14（10）：1744-1753.
LIANG Y Y，LI J B.Small objects detection method based on multi-scale non-local attention network[J].Journal of Frontiers of Computer Science and Technology，2020，14（10）：1744-1753.
[9] ZHAI S，SHANG D，WANG S，et al.DF-SSD：an improved SSD object detection algorithm based on DenseNet and feature fusion[J].IEEE Access，2020，8：24344-24357.
[10] HUANG W，LI G，CHEN Q，et al.CF2PN：a cross-scale feature fusion pyramid network based remote sensing target detection[J].Remote Sensing，2021，13（5）：847.
[11] CAO J，CHEN Q，GUO J，et al，Attention-guided context feature pyramid network for object detection[J].arXiv：2005.11475，2020.
[12] LIN T Y，DOLLáR P，GIRSHICK R，et al.Feature pyramid networks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2017：2117-2125.
[13] TAN M，PANG R，LE Q V.EfficientDet：scalable and efficient object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020：10781-10790.
[14] 汪慧兰，戴舒，刘丹，等.交通场景中改进SSD算法的小尺度行人检测研究[J].计算机工程与应用，2022，58（2）：201-207.
WANG H L，DAI S，LIU D，et al.Small-scale pedestrian detection in traffic scenes based on improved SSD algorithm[J].Computer Engineering and Applications，2022，58（2）：201-207.
[15] NIU Z，ZHONG G，YU H.A review on the attention mechanism of deep learning[J].Neurocomputing，2021，452：48-62.
[16] HU J，SHEN L，SUN G.Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：7132-7141.
[17] WOO S，PARK J，LEE J Y，et al.CBAM：convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision（ECCV），2018：3-19.
[18] VASWANI A，SHAZEER N，PARMAR N，et al.Attention is all you need[C]//Advances in Neural Information Processing System，2017：5998-6008.
[19] XUE H，LIU C，WAN F，et al.DANet：divergent activation for weakly supervised object localization[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision，2019：6589-6598.
[20] DAI Y，GIESEKE F，OEHMCKE S，et al.Attentional feature fusion[C]//Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision，2021：3560-3569.
[21] LIM J S，ASTRID M，YOON H J，et al.Small object detection using context and attention[C]//2021 International Conference on Artificial Intelligence in Information and Communication（ICAIIC），2021：181-186.
[22] LUO X，LI X，WU Y，et al.Research on change detection method of high-resolution remote sensing images based on subpixel convolution[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing，2020，14：1447-1457.
[23] ZHU Z，LIANG D，ZHANG S，et al.Traffic-sign detection and classification in the wild[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2016：2110-2118.