基于自适应实例优化的弱监督目标检测算法

doi:10.3778/j.issn.1002-8331.2204-0123

摘要/Abstract

摘要： 针对现有弱监督目标检测算法存在局部最优问题，提出一种基于上下文感知和自适应多实例细化相结合的弱监督目标检测算法。设计全局上下文注意力模块激活目标对象的整体特征，缓解局部区域支配问题；提出参数化空间丢失模块，利用生成掩模遮挡最具辨别力的区域，避免检测器将其所在的候选区域作为目标对象，从而使模型跳出局部最优解，以便选出包含更完整目标对象的候选框；通过引入自适应监督聚合函数，动态改变聚合标准，挖掘出用于训练在线细化分支的有效监督，并经过多次迭代优化提升检测性能。实验结果表明，在Pascal VOC 2007和VOC 2012数据集上检测精度分别为52.1%、46.6%；定位精度分别为68.1%、66.4%，优于已有检测算法，且有效解决了局部最优问题。

关键词: 局部显著, 上下文感知, 自适应多实例细化, 自适应监督聚合函数

Abstract: Aiming at the local optimization problem in the existing weakly supervised object detection algorithms, a weakly supervised object detection algorithm based on context-aware and adaptive multiple instance refinement is proposed in this paper. A global contextual attention module is designed to activate the whole features of the target object and alleviate the part domination problem. A parametric spatial dropout module is proposed to block the most discriminative region by utilizing the generate mask for preventing the detector taking the most discriminative region as the target object, which can conductive to jump out of the local optimal solution and meanwhile select the better candidate boxes with more complete target object. An adaptive supervised aggregation function is introduced to dynamically change the aggregation criteria, and then the effective supervision for training the online refinement branch is mined, which will improve the detection performance after several iterations. The experimental results illustrate that the detection accuracy on the Pascal VOC 2007 and VOC 2012 datasets is 52.1% and 46.6%, respectively; the localization accuracy is 68.1% and 66.4%, respectively, which are better than the existing detection algorithms and effectively solve the local optimal problem.

Key words: local saliency, context awareness, adaptive multiple instance refinement, adaptive supervised aggregation function

刘洲峰, 王凯华, 田博, 李春雷. 基于自适应实例优化的弱监督目标检测算法[J]. 计算机工程与应用, 2023, 59(17): 132-142.

LIU Zhoufeng, WANG Kaihua, TIAN Bo, LI Chunlei. Weakly Supervised Object Detection Algorithm Based on Adaptive Instance Optimization[J]. Computer Engineering and Applications, 2023, 59(17): 132-142.

参考文献

[1] 王鑫鹏，王晓强，林浩，等.深度学习典型目标检测算法的改进综述[J].计算机工程与应用，2022，58（6）：42-57.
WANG X P，WANG X Q，LIN H，et al.Review on improvement of typical object detection algorithms in deep learning[J].Computer Engineering and Applications，2022，58（6）：42-57.
[2] REN S，HE K，GIRSHICK R，et al.Faster R-CNN：towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis & Machine Intelligence，2017，39（6）：1137-1149.
[3] TAN M，PANG R，LE Q V.Efficientdet：scalable and efficient object detection[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR），2020：10781-10790.
[4] LAW H，DENG J.Cornernet：detecting objects as paired keypoints[J].International Journal of Computer Vision，2020：642-656.
[5] 朱杰，王建立，王斌.基于YOLOv4-tiny改进的轻量级口罩检测算法[J].液晶与显示，2021，36（11）：10-16.
ZHU J，WANG J L，WANG B.Improved lightweight mask detection algorithm based on YOLOv4-tiny[J].Liquid Crystal and Display，2021，36（11）：10-16.
[6] 钱伍，王国中，李国平.改进YOLOv5的交通灯实时检测鲁棒算法[J].计算机科学与探索，2022，16（1）：231-241.
QIAN W，WANG G Z，LI G P.Improved YOLOv5 traffic light real-time detection robust algorithm[J].Journal of Frontiers of Computer Science and Technology，2022，16（1）：231-241.
[7] 罗汉武，李文震，潘富城，等.基于渐进对抗学习的弱监督目标定位[J].计算机工程与应用，2021，57（14）：187-193.
LUO H W，LI W Z，PAN F C，et al.Progressive adversarial learning for weakly supervised object localization[J].Computer Engineering and Applications，2021，57（14）：187-193.
[8] 杨辉，权冀川，梁新宇，等.基于弱监督学习的目标检测研究进展[J].计算机工程与应用，2021，57（16）：40-49.
YANG H，QUAN J C，LIANG X Y，et al.Research progress of object detection based on weakly supervised learning[J].Computer Engineering and Applications，2021，57（16）：40-49.
[9] UIJLINGS J R R，VAN DE SANDE K E A，GEVERS T，et al.Selective search for object recognition[J].International Journal of Computer Vision，2013，104（2）：154-171.
[10] XIA R，LI G，HUANG Z，et al.CBASH：combined backbone and advanced selection heads with object semantic proposals for weakly supervised object detection[J].IEEE Transactions on Circuits and Systems for Video Technology，2022，32（10）：6502-6514.
[11] BILEN H，VEDALDI A.Weakly supervised deep detection networks[C]//IEEE Conference on Computer Vision & Pattern Recognition，2016：2846-2854.
[12] TANG P，WANG X，BAI X，et al.Multiple instance detection network with online instance classifier refinement[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：2843-2851.
[13] TANG P，WANG X，BAI S，et al.PCL：proposal cluster learning for weakly supervised object detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2018，42（1）：176-191.
[14] DIBA A，SHARMA V，PAZANDEH A，et al.Weakly supervised cascaded convolutional networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：914-922.
[15] WAN F，LIU C，KE W，et al.C-MIL：continuation multiple instance learning for weakly supervised object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2019：2199-2208.
[16] HE K，ZHANG X，REN S，et al.Spatial pyramid pooling in deep convolutional networks for visual recognition[J].IEEE Transactions on Pattern Analysis & Machine Intelligence，2014，37（9）：1904-1916.
[17] ZENI L F，JUNG C R.Distilling knowledge from refinement in multiple instance detection networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops，2020：768-769.
[18] WANG X，GIRSHICK R，GUPTA A，et al.Non-local neural networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：7794-7803.
[19] FENG X，YAO X，CHENG G，et al.SAENet：self-supervised adversarial and equivariant network for weakly supervised object detection in remote sensing images[J].IEEE Transactions on Geoscience and Remote Sensing，2021，60：5610411.
[20] GHIASI G，LIN T Y，LE Q V.Dropblock：a regularization method for convolutional networks[C]//Advances in Neural Information Processing Systems，2018.
[21] EVERINGHAM M R，ESLAMI S，GOOL L J，et al.The pascal visual object classes challenge[J].International Journal of Computer Vision，2015，111（1）：98-136.
[22] SHETTY S.Application of convolutional neural network for image classification on pascal voc challenge 2012 dataset[J].arXiv：1607.03785，2016.
[23] REN Z，YU Z，YANG X，et al.Instance-aware，context-focused，and memory-efficient weakly supervised object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020：10598-10607.
[24] JIE H，LI S，GANG S，et al.Squeeze-and-excitation networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2020，42（8）：2011-2023.
[25] 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.
[26] WEI Y，SHEN Z，CHENG B，et al.Ts2c：tight box mining with surrounding segmentation context for weakly supervised object detection[C]//Proceedings of the European Conference on Computer Vision（ECCV），2018：434-450.
[27] TANG P，WANG X，WANG A，et al.Weakly supervised region proposal network and object detection[C]//Proceedings of the European Conference on Computer Vision（ECCV），2018：352-368.
[28] WAN F，WEI P，JIAO J，et al.Min-entropy latent model for weakly supervised object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：1297-1306.
[29] KANTOROV V，OQUAB M，CHO M，et al.Contextlocnet：context-aware deep network models for weakly supervised localization[C]//European Conference on Computer Vision.Cham：Springer，2016：350-365.
[30] SHEN Y，JI R，WANG Y，et al.Cyclic guidance for weakly supervised joint detection and segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2019：697-707.
[31] WANG J，YAO J，ZHANG Y，et al.Collaborative learning for weakly supervised object detection[C]//Twenty-Seventh International Joint Conference on Artificial Intelligence，2018.