摘要
针对语义分割中全卷积神经网络解码器部分特征融合低效的问题,设计一种增强特征融合的解码器。级联深层特征与降维后的浅层特征,经过卷积运算后引入自身平方项的注意力机制,通过卷积预测自身项与自身平方项各通道的权重,利用乘法增强后对结果进行作和。基于pascal voc2012数据集的实验结果表明,该解码器相比原网络mIoU指标提升2.14%,结合不同特征融合方式的解码结果也验证了其性能优于同一框架下的其他对比方法。
To address the inefficient fusion of part of features in full Convolutional Neural Network(CNN)decoder in semantic segmentation,this paper proposes an enhanced feature fusion decoder.The decoder cascades high-level features and low-level features after dimensionality reduction.Then,after the convolution operations,it introduces the attention mechanism of its squared term,and predicts the weights of each channel of its own term and its squared term by convolution.Finally,the weights are enhanced by multiplication and added to get a sum.Experimental results on the pascal voc2012 dataset show that,compared with the original network,the proposed method increases the value of mIoU index by 2.14%.Decoding results under different ways of feature fusion also demonstrates that it outperforms other methods under the same framework.
作者
马震环
高洪举
雷涛
MA Zhenhuan;GAO Hongju;LEI Tao(Institute of Optics and Electronics,Chinese Academy of Sciences,Chengdu 610209,China;School of Electronic,Electrical and Communication Engineering,University of Chinese Academy of Sciences,Beijing 100049,China;32183 Troops,Jinzhou,Liaoning 121000,China)
出处
《计算机工程》
CAS
CSCD
北大核心
2020年第5期254-258,266,共6页
Computer Engineering
基金
中国科学院青年创新促进会基金(2016336)。
关键词
语义分割
卷积神经网络
解码器
特征融合
注意力机制
semantic segmentation
Convolutional Neural Network(CNN)
decoder
feature fusion
attention mechanism