摘要
针对现有的实例分割算法对有遮挡以及模糊实例检测精度低、掩码较粗糙以及泛化能力弱的问题,提出一种基于Fastformer和自监督对比学习的实例分割算法。首先,在特征提取网络之后加入基于加性注意力的Fastformer模块,并对每一层特征图中的像素点之间的相互关系进行深入建模,以提高算法对特征图全局信息的提取能力;其次,受自监督学习启发,加入自监督对比学习模块对图像中的实例进行自监督对比学习,以提高算法对图像的理解能力,从而改善在噪声干扰较多的环境下的分割效果。在Cityscapes和COCO2017数据集上的实验结果表明,相较于近期经典的实例分割算法SOLOv2(Segmenting Objects by LOcations v2),所提算法的平均精度均值(mAP)分别提高了3.1和2.5个百分点,并在实时性和精度之间达到较好的平衡,在比较复杂的场景实例分割中具有较好的鲁棒性。
To address problems of low detection precision,coarse masks and weak generalization ability of the existing instance segmentation algorithms for occluded and blurred instances,an instance segmentation algorithm based on Fastformer and self-supervised contrastive learning was proposed.Firstly,in order to enhance the ability of algorithm to extract global information of feature maps,the Fastformer module based on additive attention was added after feature extraction network,and interrelationship between pixels in each layer of feature map was modeled deeply.Secondly,inspired by self-supervised learning,a self-supervised contrastive learning module was added to conduct self-supervised contrastive learning to instances in images to enhance the ability of algorithm to understand images,thereby improving segmentation results in environments with much noise interference.Experimental results show that the proposed algorithm has the mean Average Precision(mAP)improved by 3.1 and 2.5 percentage points respectively,compared to recently classical instance segmentation algorithm SOLOv2(Segmenting Objects by LOcations v2)on Cityscapes dataset and COCO2017 dataset.And a great balance is achieved between real-time performance and precision by the proposed algorithm,leading good robustness in segmentation instance of complex scenes.
作者
高榕
沈加伟
邵雄凯
吴歆韵
GAO Rong;SHEN Jiawei;SHAO Xiongkai;WU Xinyun(School of Computer Science,Hubei University of Technology,Wuhan Hubei 430068,China;State Key Laboratory for Novel Software Technology(Nanjing University),Nanjing Jiangsu 210023,China)
出处
《计算机应用》
CSCD
北大核心
2023年第4期1062-1070,共9页
journal of Computer Applications
基金
国家自然科学基金资助项目(61902116)
南京大学计算机软件新技术国家重点实验室开放课题(KFKT2021B12)
湖北省高层次人才基金资助项目(GCRC2020011)
湖北工业大学博士科研启动基金资助项目(BSQD2019026,BSQD2019022)。
