Clothing Parsing Based on Multi-Scale Fusion and Improved Self-Attention Mechanism  

作　　者：陈诺 王绍宇 陆然 李文萱 覃志东 石秀金 CHEN Nuo;WANG Shaoyu;LU Ran;LI Wenxuan;QIN Zhidong;SHI Xiujin(College of Computer Science and Technology,Donghua University,Shanghai 201620,China)

机构地区：[1]College of Computer Science and Technology,Donghua University,Shanghai 201620,China

出　　处：《Journal of Donghua University(English Edition)》2023年第6期661-666,共6页东华大学学报（英文版）

摘　　要：Due to the lack of long-range association and spatial location information,fine details and accurate boundaries of complex clothing images cannot always be obtained by using the existing deep learning-based methods.This paper presents a convolutional structure with multi-scale fusion to optimize the step of clothing feature extraction and a self-attention module to capture long-range association information.The structure enables the self-attention mechanism to directly participate in the process of information exchange through the down-scaling projection operation of the multi-scale framework.In addition,the improved self-attention module introduces the extraction of 2-dimensional relative position information to make up for its lack of ability to extract spatial position features from clothing images.The experimental results based on the colorful fashion parsing dataset(CFPD)show that the proposed network structure achieves 53.68%mean intersection over union(mIoU)and has better performance on the clothing parsing task.

关 键 词：clothing parsing convolutional neural network multi-scale fusion self-attention mechanism vision Transformer 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]