摘要
针对目前实例分割领域掩膜表示高复杂度的问题,提出一种新的图像实例掩膜表征方法,使用3个不依赖于任何先验信息的表征单元表示并预测掩膜,且以非线性解码的形式复原掩膜,该方法可显著降低图像实例掩膜的表示复杂度和推理运算量.基于这种表示方法,构建一个高效的单阶段实例分割模型,实验结果表明,相对于其他单阶段实例分割模型,该模型在保证时间开销基本相同的情况下能获得更好的性能.此外,将该表征方法以最小改动嵌入经典模型BlendMask以重建注意力图,改进的模型相对于原模型的推理速度更快,掩膜平均精度提升1.5%,表明该表征方法通用性较好.
Aiming at the problem of high complexity in mask representation in the field of instance segmentation,we proposed a new mask representation method for instance segmentation,which used three repsesentation units that did not rely on any prior information to represent and predict mask,and restored the mask in the form of nonlinear decoding.This method could significantly reduce the representation complexity and inference computation of image instance masks.Ba sed on the representation method,we constructed an efficient single-shot instance segmentation model.The experimental results show that compared to other single-shot instance segmentation models,the model can achieve better performance while ensuring that the time cost is basically the same.Additionally,we embed the representation method with minimal modifications into the classic model BlendMask to reconstruct attention maps.The improved model has a faster inference speed compared to the original model,and the average accuracy of the mask is improved by 1.5%,indicating that the representation method has good universality.
作者
李文举
李文辉
LI Wenju;LI Wenhui(College of Computer Science and Technology,Jilin University,Changchun 130012,China)
出处
《吉林大学学报（理学版）》
CAS
北大核心
2023年第4期883-889,共7页
Journal of Jilin University:Science Edition
基金
吉林省科技发展计划项目(批准号:20230201082GX).
关键词
深度学习
实例分割
压缩表示
表征单元
deep learning
instance segmentation
compressed representation
representation unit
