液晶与显示2025，Vol.40Issue(5)：740-750,11.DOI:10.37188/CJLCD.2024-0288
基于深度度量学习和语义分割的场景识别
Scene recognition based on deep metric learning and semantic segmentation
摘要
Abstract
To address the issue of low recognition accuracy in scene images caused by subtle inter-class differences and ambiguous intra-class classifications,this paper proposes a novel semantic segmentation framework.By introducing deep metric learning and focusing on the semantic relationships between pixels,the model's recognition accuracy can be improved.Firstly,feature extraction is performed through the hollow space pyramid pooling module.Then,in the decoding process,the shallow high-resolution features and deep low resolution features are fused using a structure to better restore the details and boundaries in the image.Secondly,in the deep metric learning module,a well structured pixel semantic embedding space is learned to effectively classify pixels by maximizing the Euclidean distance between pixels of different categories and minimizing the Euclidean distance between pixels of the same category.Finally,a fusion loss function combining weighted focus loss and contrast loss is adopted to balance the importance between different samples,thereby more accurately measuring the performance of the model and improving the accuracy and robustness of scene recognition.The experimental results demonstrate that the average intersection to union ratios of the model on the publicly available datasets ADE20K and Cityscapes are 47.6%and 83.1%,respectively.Compared with the baseline of today's advanced scene recognition methods,the results show that the proposed method is feasible and progressiveness.关键词
深度学习/深度度量学习/语义分割/场景识别/类不平衡Key words
deep learning/deep metric learning/semantic segmentation/scene recognition/class imbalance分类
计算机与自动化引用本文复制引用
贾轩,张叶,常旭岭,孙建波..基于深度度量学习和语义分割的场景识别[J].液晶与显示,2025,40(5):740-750,11.基金项目
国防科技创新特区项目(No.18-H863-00-TS-002-018-01) Supported by National Defense Science and Technology Innovation Special Zone Project(No.18-H863-00-TS-002-018-01) （No.18-H863-00-TS-002-018-01）
