电子科技2024，Vol.37Issue(7)：25-32,8.DOI:10.16180/j.cnki.issn1007-7820.2024.07.004
基于关键区域特征提取与二阶段分类网络的场景识别方法
Scene Recognition Algorithm Based on Discriminative Patch Extraction and Two-Stage Classification
摘要
Abstract
In the scene recognition task,there are cases where heterogeneous scenes contain items with high similarity or the spatial layout of similar scenes is too different,that is,the inter-class similarity and intra-class difference of scenes.Existing methods improve the discriminant ability of classifiers by enhancing data sets or using multi-level information complementation.Although some improvements have been made,there are still limitations.In this study,the DPE(Discriminative Patch Extraction)and TSC(Two-Stage Classification)network method are proposed to overcome the inter-class similarity and intra-class difference of scenes.DPE avoids the impact of intra-class differences on scene recognition by preserving the key information regions in images,while the TSC net-work avoids the impact of inter-class similarities on scene recognition by the coarse-fine two-stage training.After combining the proposed method with baseline networks such as ViT(Vision Transformer),the classification accuracy of classical scene recognition data sets Scene15,MITindoor67 and SUN397 reaches 96.9%,88.4%and 76.0%,respectively.The proposed method achieves the highest classification accuracy of 60.5%on the largest scene recog-nition dataset Places365.关键词
场景识别/深度神经网络/类间相似/类内差异/数据增强/关键区域特征提取/二阶段分类/ViTKey words
scene recognition/deep neural networks/inter-class similarity/intra-class variability/data augmentation/discriminative patch extraction/two-stage classification/ViT分类
信息技术与安全科学引用本文复制引用
韩瀛昊,李菲菲..基于关键区域特征提取与二阶段分类网络的场景识别方法[J].电子科技,2024,37(7):25-32,8.基金项目
上海市高校特聘教授(东方学者)岗位计划(ES2015XX)Program for Professor of Special Appointment(Eastern Scholar)at Shanghai Institutions of Higher Learning(ES2015XX) （东方学者）
