计算机工程与应用2024，Vol.60Issue(4)：142-152,11.DOI:10.3778/j.issn.1002-8331.2209-0156
高效跨域的Transformer小样本语义分割网络
Efficient Cross-Domain Transformer Few-Shot Semantic Segmentation Network
摘要
Abstract
Few-shot semantic segmentation aims at only using several labeling samples to learn target features and com-plete the semantic segmentation task.The main problems in mainstream research are low training efficiency,meta training and meta testing in the same data domain.For this task,this paper proposes an efficient,cross-domain few-shot semantic segmentation network based on Transformer:SGFNet.In the encoding layer,use the shared weight MixVisionTransformer to build a siamese network to extract the support set and query set image features.In the relationship calculation layer,cal-culate the Hadamard product of the support set image feature vector and its corresponding mask to extract the target fea-ture maps,and calculate the relationship between them and the image features of the query set.In the decoder layer,im-prove the MLP decoder and propose a residual decoder to decode the features of different hierarchies to obtain the final segmentation result.Experiments show that the model only needs to use a single 3090 GPU on the FSS-1000 dataset for training 1.5～4.0 h to get the optimal result 1-shot mIoU 87.0%on PASCAL-5i and the COCO-20i dataset perform cross-domain tests to achieve non-cross-domain effects,the 1-shot mIoU is 60.4%and 33.0%,respectively,proving that the model is efficient and cross-domain.关键词
小样本语义分割(FSS)/跨域/Transformer/小样本学习(FSL)/语义分割Key words
few-shot semantic segmentation(FSS)/cross-domain/transformer/few-shot learning(FSL)/semantic seg-mentation分类
信息技术与安全科学引用本文复制引用
方红,李德生,蒋广杰..高效跨域的Transformer小样本语义分割网络[J].计算机工程与应用,2024,60(4):142-152,11.基金项目
国家自然科学基金面上项目(11971299) （11971299）
中国高校产学研创新基金(2021ITA03008) （2021ITA03008）
电子信息类专业硕士协同创新平台建设项目(A10GY21F015). （A10GY21F015）
