吉林大学学报（理学版）2025，Vol.63Issue(3)：795-803,9.DOI:10.13413/j.cnki.jdxblxb.2023554
基于空间金字塔注意力的细粒度图像分类
Fine-Grained Image Classification Based on Spatial Pyramid Attention
摘要
Abstract
Based on an improved spatial pyramid attention module,we enhanced the performance of lightweight networks in fine-grained image classification tasks.By combining global and local features,the improved model enhanced the classification performance of lightweight networks without significantly increasing the number of parameters.The experimental results on the Stanford Dogs dataset show that the lightweight network equipped with this module significantly improves accuracy,even surpassing some classical models.This method expands the application scope of lightweight networks on resource-constrained devices and provides an efficient and low-computational-cost solution for fine-grained image classification problems.关键词
图像分类/细粒度分类/注意力机制/轻量化网络Key words
image classification/fine-grained classification/attention mechanism/lightweight network分类
信息技术与安全科学引用本文复制引用
朱丽,潘鑫,付海涛,杨亚杰,金晨磊,冯宇轩,范健..基于空间金字塔注意力的细粒度图像分类[J].吉林大学学报（理学版）,2025,63(3):795-803,9.基金项目
吉林省科技发展计划项目(批准号:20240302092GX)和吉林省教育厅科学技术研究项目(批准号:JJKH20250569KJ). （批准号:20240302092GX）
