湖南工业大学学报2025，Vol.39Issue(5)：58-66,9.DOI:10.3969/j.issn.1673-9833.2025.05.009
TF-ME:多尺度特征增强的透明物体分割网络
TF-ME:Transparent Object Segmentation Network with Multi-Scale Feature Enhancement
摘要
Abstract
In view of the transparent objects inheriting information from the background and the limitation of receptive fields in traditional convolutional neural networks,a transparent object segmentation network TF-ME has been proposed based on Transformer and multi-scale feature enhancement.The model adopts a hybrid structure of CNN and Transformer.In the feature extraction stage,a multi-scale feature fusion module is designed to effectively integrate global and local information,thus improving the segmentation effect of the model on transparent objects of different sizes.In addition,the feedforward neural network is redesigned for an enhancement of the context understanding ability of the Transformer encoder,followed by comparative experiments conducted on the Trans10K-v2 dataset for a verification of the effectiveness of the proposed algorithm.The experimental results show that the proposed method achieves 94.68%ACC and 73.39%MIoU in 11 types of transparent object segmentation,respectively.Compared with other algorithms,the performance of the proposed model has been significantly improved.关键词
透明物体/语义分割/Transformer/前馈神经网络/特征融合Key words
transparent object/semantic segmentation/Transformer/feedforward neural network/feature fusion分类
计算机与自动化引用本文复制引用
郭扬,邓晓军,肖世康,孙元昊..TF-ME:多尺度特征增强的透明物体分割网络[J].湖南工业大学学报,2025,39(5):58-66,9.基金项目
湖南省自然科学基金资助项目(2024JJ7148) （2024JJ7148）
