A Self-Supervised Tree-Structured Framework for Fine-Grained Classification
In computer vision, fine-grained classification has become an important issue in recognizing objects with slight visual differences. Usually, it is challenging to generate good performance when solving fine-grained classification problems using traditional convolutional neural networks. To improve t...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/7/4453 |
| _version_ | 1797608324694278144 |
|---|---|
| author | Qihang Cai Lei Niu Xibin Shang Heng Ding |
| author_facet | Qihang Cai Lei Niu Xibin Shang Heng Ding |
| author_sort | Qihang Cai |
| collection | DOAJ |
| description | In computer vision, fine-grained classification has become an important issue in recognizing objects with slight visual differences. Usually, it is challenging to generate good performance when solving fine-grained classification problems using traditional convolutional neural networks. To improve the accuracy and training time of convolutional neural networks in solving fine-grained classification problems, this paper proposes a tree-structured framework by eliminating the effect of differences between clusters. The contributions of the proposed method include the following three aspects: (1) a self-supervised method that automatically creates a classification tree, eliminating the need for manual labeling; (2) a machine-learning matcher which determines the cluster to which an item belongs, minimizing the impact of inter-cluster variations on classification; and (3) a pruning criterion which filters the tree-structured classifier, retaining only the models with superior classification performance. The experimental evaluation of the proposed tree-structured framework demonstrates its effectiveness in reducing training time and improving the accuracy of fine-grained classification across various datasets in comparison with conventional convolutional neural network models. Specifically, for the CUB 200 2011, FGVC aircraft, and Stanford car datasets, the proposed method achieves a reduction in training time of 32.91%, 35.87%, and 14.48%, and improves the accuracy of fine-grained classification by 1.17%, 2.01%, and 0.59%, respectively. |
| first_indexed | 2024-03-11T05:41:52Z |
| format | Article |
| id | doaj.art-632fc917027d4ec084fd0f375a91b832 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T05:41:52Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-632fc917027d4ec084fd0f375a91b8322023-11-17T16:20:32ZengMDPI AGApplied Sciences2076-34172023-03-01137445310.3390/app13074453A Self-Supervised Tree-Structured Framework for Fine-Grained ClassificationQihang Cai0Lei Niu1Xibin Shang2Heng Ding3Central China Normal University Wollongong Joint Institute, Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan 430079, ChinaCentral China Normal University Wollongong Joint Institute, Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan 430079, ChinaCentral China Normal University Wollongong Joint Institute, Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan 430079, ChinaCentral China Normal University Wollongong Joint Institute, Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan 430079, ChinaIn computer vision, fine-grained classification has become an important issue in recognizing objects with slight visual differences. Usually, it is challenging to generate good performance when solving fine-grained classification problems using traditional convolutional neural networks. To improve the accuracy and training time of convolutional neural networks in solving fine-grained classification problems, this paper proposes a tree-structured framework by eliminating the effect of differences between clusters. The contributions of the proposed method include the following three aspects: (1) a self-supervised method that automatically creates a classification tree, eliminating the need for manual labeling; (2) a machine-learning matcher which determines the cluster to which an item belongs, minimizing the impact of inter-cluster variations on classification; and (3) a pruning criterion which filters the tree-structured classifier, retaining only the models with superior classification performance. The experimental evaluation of the proposed tree-structured framework demonstrates its effectiveness in reducing training time and improving the accuracy of fine-grained classification across various datasets in comparison with conventional convolutional neural network models. Specifically, for the CUB 200 2011, FGVC aircraft, and Stanford car datasets, the proposed method achieves a reduction in training time of 32.91%, 35.87%, and 14.48%, and improves the accuracy of fine-grained classification by 1.17%, 2.01%, and 0.59%, respectively.https://www.mdpi.com/2076-3417/13/7/4453fine-grained classificationtree-structured frameworkmachine-learning matcherconvolutional neural network |
| spellingShingle | Qihang Cai Lei Niu Xibin Shang Heng Ding A Self-Supervised Tree-Structured Framework for Fine-Grained Classification Applied Sciences fine-grained classification tree-structured framework machine-learning matcher convolutional neural network |
| title | A Self-Supervised Tree-Structured Framework for Fine-Grained Classification |
| title_full | A Self-Supervised Tree-Structured Framework for Fine-Grained Classification |
| title_fullStr | A Self-Supervised Tree-Structured Framework for Fine-Grained Classification |
| title_full_unstemmed | A Self-Supervised Tree-Structured Framework for Fine-Grained Classification |
| title_short | A Self-Supervised Tree-Structured Framework for Fine-Grained Classification |
| title_sort | self supervised tree structured framework for fine grained classification |
| topic | fine-grained classification tree-structured framework machine-learning matcher convolutional neural network |
| url | https://www.mdpi.com/2076-3417/13/7/4453 |
| work_keys_str_mv | AT qihangcai aselfsupervisedtreestructuredframeworkforfinegrainedclassification AT leiniu aselfsupervisedtreestructuredframeworkforfinegrainedclassification AT xibinshang aselfsupervisedtreestructuredframeworkforfinegrainedclassification AT hengding aselfsupervisedtreestructuredframeworkforfinegrainedclassification AT qihangcai selfsupervisedtreestructuredframeworkforfinegrainedclassification AT leiniu selfsupervisedtreestructuredframeworkforfinegrainedclassification AT xibinshang selfsupervisedtreestructuredframeworkforfinegrainedclassification AT hengding selfsupervisedtreestructuredframeworkforfinegrainedclassification |