计算机科学
循环神经网络
编码器
人工智能
卷积神经网络
解码方法
变压器
分割
模式识别(心理学)
图像分割
特征提取
特征(语言学)
卷积码
计算机视觉
人工神经网络
算法
工程类
语言学
哲学
电压
电气工程
操作系统
作者
Xinxin Shan,Tai Ma,GU An-qi,Haibin Cai,Ying Wen
标识
DOI:10.1109/icassp43922.2022.9747716
摘要
Recently, several Transformer-based methods have been presented to improve image segmentation. However, since Transformer needs regular square images and has difficulty in obtaining local feature information, the performance of image segmentation is seriously affected. In this paper, we propose a novel encoder-decoder network named TCRNet, which makes Transformer, Convolutional neural network (CNN) and Recurrent neural network (RNN) complement each other. In the encoder, we extract and concatenate the feature maps from Transformer and CNN to effectively capture global and local feature information of images. Then in the decoder, we utilize convolutional RNN in the proposed recurrent decoding unit to refine the feature maps from the decoder for finer prediction. Experimental results on three medical datasets demonstrate that TCRNet effectively improves the segmentation precision.
科研通智能强力驱动
Strongly Powered by AbleSci AI