http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
A Deep Learning-Based Image Semantic Segmentation Algorithm
Chaoqun Shen,Zhongliang Sun 한국정보처리학회 2023 Journal of information processing systems Vol.19 No.1
This paper is an attempt to design segmentation method based on fully convolutional networks (FCN) andattention mechanism. The first five layers of the Visual Geometry Group (VGG) 16 network serve as the codingpart in the semantic segmentation network structure with the convolutional layer used to replace pooling toreduce loss of image feature extraction information. The up-sampling and deconvolution unit of the FCN isthen used as the decoding part in the semantic segmentation network. In the deconvolution process, the skipstructure is used to fuse different levels of information and the attention mechanism is incorporated to reduceaccuracy loss. Finally, the segmentation results are obtained through pixel layer classification. The results showthat our method outperforms the comparison methods in mean pixel accuracy (MPA) and mean intersectionover union (MIOU).