{"title":"Naming conventions-based multi-label and multi-task learning for fine-grained classification","authors":"Qinbang Zhou, Kezhi Zhang, Feng Yue, Zhaoliang Zhang, Hui Yu","doi":"10.1117/12.3014589","DOIUrl":null,"url":null,"abstract":"This paper proposes a fine-grained image classification architecture using multi-task learning. The structure of the fine-grained classification network uses ResNest as the feature extraction layer of the multi-task hard parameter sharing mode with the fine-grained category label regression branch based on multi-hot naming conventions and classification branch based on cross-entropy loss with one-hot encoding. The coupling between the two branches enables multi-task classification through hyperparameter weighting. Subsequently, comparison and ablation experiments were performed on the public datasets of Stanford Cars, CUB-200-2011 and FGVC-Aircraft. The experimental result shows multi-label regression, multi-task learning and label smoothing can effectively improve the generalization of the model and increase the inter-class distance of the previous layer at the network output terminal, and reduces the intra-class distance.","PeriodicalId":516634,"journal":{"name":"International Conference on Algorithm, Imaging Processing and Machine Vision (AIPMV 2023)","volume":" 30","pages":"129691D - 129691D-7"},"PeriodicalIF":0.0000,"publicationDate":"2024-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Conference on Algorithm, Imaging Processing and Machine Vision (AIPMV 2023)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1117/12.3014589","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
This paper proposes a fine-grained image classification architecture using multi-task learning. The structure of the fine-grained classification network uses ResNest as the feature extraction layer of the multi-task hard parameter sharing mode with the fine-grained category label regression branch based on multi-hot naming conventions and classification branch based on cross-entropy loss with one-hot encoding. The coupling between the two branches enables multi-task classification through hyperparameter weighting. Subsequently, comparison and ablation experiments were performed on the public datasets of Stanford Cars, CUB-200-2011 and FGVC-Aircraft. The experimental result shows multi-label regression, multi-task learning and label smoothing can effectively improve the generalization of the model and increase the inter-class distance of the previous layer at the network output terminal, and reduces the intra-class distance.